source: other-projects/nightly-tasks/diffcol/trunk/gs3-model-collect/Word-PDF-Formatting/archives/HASHeaa2.dir/doc.xml@ 38996

Last change on this file since 38996 was 38996, checked in by anupama, 5 weeks ago

SourceDirectory seems to be new metadata in doc.xml that is breaking diffcol (when diffcol attempted on Win VM)
File size: 246.2 KB
Line 
1<?xml version="1.0" encoding="utf-8" standalone="no"?>
2<!DOCTYPE Archive SYSTEM "https://greenstone.org/dtd/Archive/1.0/Archive.dtd">
3<Archive>
4<Section>
5 <Description>
6 <Metadata name="gsdldoctype">indexed_doc</Metadata>
7 <Metadata name="SourceDirectory">/Scratch/ak19/gs3-svn-02May2024/web/sites/localsite/collect/Word-PDF-Formatting/tmp/1714976079_4</Metadata>
8 <Metadata name="Language">en</Metadata>
9 <Metadata name="Encoding">utf8</Metadata>
10 <Metadata name="GENERATOR">wvWare/wvWare version 1.2.4</Metadata>
11 <Metadata name="Title">1997-00 Listing of Working Papers</Metadata>
12 <Metadata name="URL">http://Scratch/ak19/gs3-svn-02May2024/web/sites/localsite/collect/Word-PDF-Formatting/tmp/1714976079_4/word01.html</Metadata>
13 <Metadata name="UTF8URL">http://Scratch/ak19/gs3-svn-02May2024/web/sites/localsite/collect/Word-PDF-Formatting/tmp/1714976079_4/word01.html</Metadata>
14 <Metadata name="gsdlsourcefilename">import/word01.doc</Metadata>
15 <Metadata name="gsdlsourcefilerenamemethod">url</Metadata>
16 <Metadata name="gsdlconvertedfilename">tmp/1714976079_4/word01.html</Metadata>
17 <Metadata name="OrigSource">word01.html</Metadata>
18 <Metadata name="Source">word01.doc</Metadata>
19 <Metadata name="SourceFile">word01.doc</Metadata>
20 <Metadata name="Plugin">WordPlugin</Metadata>
21 <Metadata name="FileSize">110080</Metadata>
22 <Metadata name="SourceDirectory">.</Metadata>
23 <Metadata name="FilenameRoot">word01</Metadata>
24 <Metadata name="FileFormat">Word</Metadata>
25 <Metadata name="srcicon">_icondoc_</Metadata>
26 <Metadata name="srclink_file">doc.doc</Metadata>
27 <Metadata name="srclinkFile">doc.doc</Metadata>
28 <Metadata name="Identifier">HASHeaa2992e081949673150f3</Metadata>
29 <Metadata name="lastmodified">1714975834</Metadata>
30 <Metadata name="lastmodifieddate">20240506</Metadata>
31 <Metadata name="oailastmodified">1714976079</Metadata>
32 <Metadata name="oailastmodifieddate">20240506</Metadata>
33 <Metadata name="assocfilepath">HASHeaa2.dir</Metadata>
34 <Metadata name="gsdlassocfile">doc.doc:application/msword:</Metadata>
35 </Description>
36 <Content>
37
38&lt;!--Section Begins--&gt;&lt;br&gt;
39
40
41
42&lt;p&gt;&lt;div name=&quot;Title&quot; align=&quot;center&quot; style=&quot;margin: 0.00mm -0.12mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
43
44&lt;p style=&quot;text-indent: 0.00mm; text-align: center; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
45&lt;b&gt;1997-00 Listing of Working Papers &lt;/b&gt;
46&lt;/p&gt;&lt;/div&gt;
47
48
49
50&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
51
52&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
53
54&lt;/p&gt;&lt;/div&gt;
55
56
57
58&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
59
60&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
61
62&lt;/p&gt;&lt;/div&gt;
63
64
65
66&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
67
68&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
69
70&lt;/p&gt;&lt;/div&gt;
71
72
73
74&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
75
76&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
772000/1
78&lt;/p&gt;&lt;/div&gt;
79
80
81
82&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
83
84&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
85Using compression to identify acronyms in text
86&lt;/p&gt;&lt;/div&gt;
87
88
89
90&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
91
92&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
93Stuart Yeates, David Bainbridge, Ian H. Witten
94&lt;/p&gt;&lt;/div&gt;
95
96
97
98&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
99
100&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
101Text mining is about looking for patterns in natural language text, and may be defined as the process of analyzing text to extract information from it for particular purposes. In previous work, we claimed that compression is a key technology for text mining, and backed this up with a study that showed how particular kinds of lexical tokens&amp;mdash;names, dates, locations, &lt;i&gt;etc.&lt;/i&gt;&amp;mdash;can be identified and located in running text, using compression models to provide the leverage necessary to distinguish different token types (Witten &lt;i&gt;et al.&lt;/i&gt;, 1999)
102&lt;/p&gt;&lt;/div&gt;
103
104
105
106&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
107
108&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
109
110&lt;/p&gt;&lt;/div&gt;
111
112
113
114&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
115
116&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1172000/2
118&lt;/p&gt;&lt;/div&gt;
119
120
121
122&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
123
124&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
125Text categorization using compression models
126&lt;/p&gt;&lt;/div&gt;
127
128
129
130&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
131
132&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
133Eibe Frank, Chang Chui, Ian H. Witten
134&lt;/p&gt;&lt;/div&gt;
135
136
137
138&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
139
140&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
141Text categorization, or the assignment of natural language texts to predefined categories based on their content, is of growing importance as the volume of information available on the internet continues to overwhelm us. The use of predefined categories implies a &amp;ldquo;supervised learning&amp;rdquo; approach to categorization, where already-classified articles - which effectively define the categories - are used as &amp;ldquo;training data&amp;rdquo; to build a model that can be used for classifying new articles that comprise the &amp;ldquo;test data&amp;rdquo;. This contrasts with &amp;ldquo;unsupervised&amp;rdquo; learning, where there is no training data and clusters of like documents are sought amongst the test articles. With supervised learning, meaningful labels (such as keyphrases) are attached to the training documents, and appropriate labels can be assigned automatically to test documents depending on which category they fall into.
142&lt;/p&gt;&lt;/div&gt;
143
144
145
146&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
147
148&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
149
150&lt;/p&gt;&lt;/div&gt;
151
152
153
154&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
155
156&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1572000/3
158&lt;/p&gt;&lt;/div&gt;
159
160
161
162&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
163
164&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
165Reserved for Sally Jo
166&lt;/p&gt;&lt;/div&gt;
167
168
169
170&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
171
172&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
173
174&lt;/p&gt;&lt;/div&gt;
175
176
177
178&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
179
180&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1812000/4
182&lt;/p&gt;&lt;/div&gt;
183
184
185
186&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
187
188&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
189Interactive machine learning&amp;mdash;letting users build classifiers
190&lt;/p&gt;&lt;/div&gt;
191
192
193
194&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
195
196&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
197Malcolm Ware, Eibe Frank, Geoffrey Holmes, Mark Hall, Ian H. Witten
198&lt;/p&gt;&lt;/div&gt;
199
200
201
202&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
203
204&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
205According to standard procedure, building a classifier is a fully automated process that follows data preparation by a domain expert. In contrast, &amp;lt;I&amp;gt;interactive&amp;lt;/I&amp;gt;machine learning engages users in actually generating the classifier themselves. This offers a natural way of integrating background knowledge into the modeling stage&amp;mdash;so long as interactive tools can be designed that support efficient and effective communication. This paper shows that appropriate techniques can empower users to create models that compete with classifiers built by state-of-the-art learning algorithms. It demonstrates that users&amp;mdash;even users who are not domain experts&amp;mdash;can often construct good classifiers, without any help from a learning algorithm, using a simple two-dimensional visual interface. Experiments demonstrate that, not surprisingly, success hinges on the domain: if a few attributes can support good predictions, users generate accurate classifiers, whereas domains with many high-order attribute interactions favor standard machine learning techniques. The future challenge is to achieve a symbiosis between human user and machine learning algorithm.
206&lt;/p&gt;&lt;/div&gt;
207
208
209
210&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
211
212&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
213
214&lt;/p&gt;&lt;/div&gt;
215
216
217
218&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
219
220&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2212000/5
222&lt;/p&gt;&lt;/div&gt;
223
224
225
226&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
227
228&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
229KEA: Practical automatic keyphrase extraction
230&lt;/p&gt;&lt;/div&gt;
231
232
233
234&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
235
236&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
237Ian H. Witten, Gordon W. Paynter, Eibe Frank, Carl Gutwin, Craig G. Nevill-Manning
238&lt;/p&gt;&lt;/div&gt;
239
240
241
242&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
243
244&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
245Keyphrases provide semantic metadata that summarize and characterize documents. This paper describes Kea, an algorithm for automatically extracting keyphrases from text. Kea identifies candidate keyphrases using lexical methods, calculates feature values for each candidate, and uses a machine learning algorithm to predict which candidates are good keyphrases. The machine learning scheme first builds a prediction model using training documents with known keyphrases, and then uses the model to find keyphrases in new documents. We use a large test corpus to evaluate Kea's effectiveness in terms of how many author-assigned keyphrases are correctly identified. The system is simple, robust, and publicly available.
246&lt;/p&gt;&lt;/div&gt;
247
248
249
250&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
251
252&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
253
254&lt;/p&gt;&lt;/div&gt;
255
256
257
258&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
259
260&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2612000/6
262&lt;/p&gt;&lt;/div&gt;
263
264
265
266&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
267
268&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
269&lt;i&gt;Ό&lt;/i&gt;-Charts and Z: hows, whys and wherefores
270&lt;/p&gt;&lt;/div&gt;
271
272
273
274&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
275
276&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
277Greg Reeve, Steve Reeves
278&lt;/p&gt;&lt;/div&gt;
279
280
281
282&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
283
284&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
285In this paper we show, by a series of examples, how the &lt;i&gt;Ό&lt;/i&gt;-chart formalism can be translated into Z. We give reasons for why this is an interesting and sensible thing to do and what it might be used for.
286&lt;/p&gt;&lt;/div&gt;
287
288
289
290&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
291
292&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
293
294&lt;/p&gt;&lt;/div&gt;
295
296
297
298&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
299
300&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
301
302&lt;/p&gt;&lt;/div&gt;
303
304
305
306&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
307
308&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3092000/7
310&lt;/p&gt;&lt;/div&gt;
311
312
313
314&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
315
316&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
317One dimensional non-uniform rational B-splines for animation control
318&lt;/p&gt;&lt;/div&gt;
319
320
321
322&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
323
324&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
325Abdelaziz Mahoui
326&lt;/p&gt;&lt;/div&gt;
327
328
329
330&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
331
332&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
333Most 3D animation packages use graphical representations called motion graphs to represent the variation in time of the motion parameters. Many use two-dimensional B-splines as animation curves because of their power to represent free-form curves. In this project, we investigate the possibility of using One-dimensional Non-Uniform Rational B-Spline (NURBS) curves for the interactive construction of animation control curves. One-dimensional NURBS curves present the potential of solving some problems encountered in motion graphs when two-dimensional B-splines are used. The study focuses on the properties of One-dimensional NURBS mathematical model. It also investigates the algorithms and shape modification tools devised for two-dimensional curves and their port to the One-dimensional NURBS model. It also looks at the issues related to the user interface used to interactively modify the shape of the curves.
334&lt;/p&gt;&lt;/div&gt;
335
336
337
338&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
339
340&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
341
342&lt;/p&gt;&lt;/div&gt;
343
344
345
346&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
347
348&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3492000/8
350&lt;/p&gt;&lt;/div&gt;
351
352
353
354&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
355
356&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
357Correlation-based feature selection of discrete and numeric class machine learning
358&lt;/p&gt;&lt;/div&gt;
359
360
361
362&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
363
364&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
365Mark A. Hall
366&lt;/p&gt;&lt;/div&gt;
367
368
369
370&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
371
372&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
373Algorithms for feature selection fall into two broad categories: &amp;lt;I&amp;gt;wrappers&amp;lt;/I&amp;gt;that use the learning algorithm itself to evaluate the usefulness of features and &amp;lt;I&amp;gt;filters&amp;lt;/I&amp;gt;that evaluate features according to heuristics based on general characteristics of the data. For application to large databases, filters have proven to be more practical than wrappers because they are much faster. However, most existing filter algorithms only work with discrete classification problems. This paper describes a fast, correlation-based filter algorithm that can be applied to continuous and discrete problems. The algorithm often out-performs the well-known ReliefF attribute estimator when used as a preprocessing step for naïve Bayes, instance-based learning, decision trees, locally weighted regression, and model trees. It performs more feature selection than ReliefF does-reducing the data dimensionality by fifty percent in most cases. Also, decision and model trees built from the prepocessed data are often significantly smaller.
374&lt;/p&gt;&lt;/div&gt;
375
376
377
378&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
379
380&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
381
382&lt;/p&gt;&lt;/div&gt;
383
384
385
386&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
387
388&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3892000/9
390&lt;/p&gt;&lt;/div&gt;
391
392
393
394&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
395
396&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
397A development environment for predictive modelling in foods
398&lt;/p&gt;&lt;/div&gt;
399
400
401
402&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
403
404&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
405G. Holmes, M.A. Hall
406&lt;/p&gt;&lt;/div&gt;
407
408
409
410&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
411
412&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
413WEKA (Waikato Environment for Knowledge Analysis) is a comprehensive suite of Java class libraries that implement many state-of-the-art machine learning/data mining algorithms. Non-programmers interact with the software via a user interface component called the Knowledge Explorer.
414&lt;/p&gt;&lt;/div&gt;
415
416
417
418&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
419
420&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
421
422&lt;/p&gt;&lt;/div&gt;
423
424
425
426&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
427
428&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
429Applications constructed from the WEKA class libraries can be run on any computer with a web browsing capability, allowing users to apply machine learning techniques to their own data regardless of computer platform. This paper describes the user interface component of the WEKA system in reference to previous applications in the predictive modeling of foods.
430&lt;/p&gt;&lt;/div&gt;
431
432
433
434&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
435
436&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
437
438&lt;/p&gt;&lt;/div&gt;
439
440
441
442&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
443
444&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
4452000/10
446&lt;/p&gt;&lt;/div&gt;
447
448
449
450&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
451
452&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
453Benchmarking attribute selection techniques for data mining
454&lt;/p&gt;&lt;/div&gt;
455
456
457
458&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
459
460&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
461Mark A. Hall, Geoffrey Holmes
462&lt;/p&gt;&lt;/div&gt;
463
464
465
466&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
467
468&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
469Data engineering is generally considered to be a central issue in the development of data mining applications. The success of many learning schemes, in their attempts to construct models of data, hinges on the reliable identification of a small set of highly predictive attributes. The inclusion of irrelevant, redundant and noisy attributes in the model building process phase can result in poor predictive performance and increased computation.
470&lt;/p&gt;&lt;/div&gt;
471
472
473
474&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
475
476&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
477
478&lt;/p&gt;&lt;/div&gt;
479
480
481
482&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
483
484&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
485Attribute selection generally involves a combination of search and attribute utility estimation plus evaluation with respect to specific learning schemes. This leads to a large number of possible permutations and has led to a situation where very few benchmark studies have been conducted.
486&lt;/p&gt;&lt;/div&gt;
487
488
489
490&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
491
492&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
493
494&lt;/p&gt;&lt;/div&gt;
495
496
497
498&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
499
500&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
501This paper presents a benchmark comparison of several attribute selection methods. All the methods produce an attribute ranking, a useful devise of isolating the individual merit of an attribute. Attribute selection is achieved by cross-validating the rankings with respect to a learning scheme to find the best attributes. Results are reported for a selection of standard data sets and two learning schemes C4.5 and naïve Bayes.
502&lt;/p&gt;&lt;/div&gt;
503
504
505
506&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
507
508&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
509
510&lt;/p&gt;&lt;/div&gt;
511
512
513
514&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
515
516&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
5172000/11
518&lt;/p&gt;&lt;/div&gt;
519
520
521
522&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
523
524&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
525Steve Reeves, Greg Reeve
526&lt;/p&gt;&lt;/div&gt;
527
528
529
530&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
531
532&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
533
534&lt;/p&gt;&lt;/div&gt;
535
536
537
538&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
539
540&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
541
542&lt;/p&gt;&lt;/div&gt;
543
544
545
546&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
547
548&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
5492000/12
550&lt;/p&gt;&lt;/div&gt;
551
552
553
554&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
555
556&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
557Malika Mahoui, Sally Jo Cunningham
558&lt;/p&gt;&lt;/div&gt;
559
560
561
562&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
563
564&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
565Transaction logs are invaluable sources of fine-grained information about users' search behavior. This paper compares the searching behavior of users across two WWW-accessible digital libraries: the New Zealand Digital Library's Computer Science Technical Reports collection (CSTR), and the Karlsruhe Computer Science Bibliographies (CSBIB) collection. Since the two collections are designed to support the same type of users-researchers/students in computer science a comparative log analysis is likely to uncover common searching preferences for that user group. The two collections differ in their content, however; the CSTR indexes a full text collection, while the CSBIB is primarily a bibliographic database. Differences in searching behavior between the two systems may indicate the effect of differing search facilities and content type.
566&lt;/p&gt;&lt;/div&gt;
567
568
569
570&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
571
572&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
573
574&lt;/p&gt;&lt;/div&gt;
575
576
577
578&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
579
580&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
581
582&lt;/p&gt;&lt;/div&gt;
583
584
585
586&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
587
588&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
589
590&lt;/p&gt;&lt;/div&gt;
591
592
593
594&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
595
596&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
597
598&lt;/p&gt;&lt;/div&gt;
599
600
601
602&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
603
604&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
605
606&lt;/p&gt;&lt;/div&gt;
607
608
609
610&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
611
612&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
613
614&lt;/p&gt;&lt;/div&gt;
615
616
617
618&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
619
620&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
62199/1
622&lt;/p&gt;&lt;/div&gt;
623
624
625
626&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
627
628&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
629Lexical attraction for text compression
630&lt;/p&gt;&lt;/div&gt;
631
632
633
634&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
635
636&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
637Joscha Bach, Ian H. Witten
638&lt;/p&gt;&lt;/div&gt;
639
640
641
642&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
643
644&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
645New methods of acquiring structural information in text documents may support better compression by identifying an appropriate prediction context for each symbol. The method of &amp;ldquo;lexical attraction&amp;rdquo; infers syntactic dependency structures from statistical analysis of large corpora. We describe the generation of a lexical attraction model, discuss its application to text compression, and explore its potential to outperform fixed-context models such as word-level PPM. Perhaps the most exciting aspect of this work is the prospect of using compression as a metric for structure discovery in text.
646&lt;/p&gt;&lt;/div&gt;
647
648
649
650&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
651
652&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
653
654&lt;/p&gt;&lt;/div&gt;
655
656
657
658&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
659
660&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
661
662&lt;/p&gt;&lt;/div&gt;
663
664
665
666&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
667
668&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
66999/2
670&lt;/p&gt;&lt;/div&gt;
671
672
673
674&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
675
676&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
677Generating rule sets from model trees
678&lt;/p&gt;&lt;/div&gt;
679
680
681
682&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
683
684&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
685Geoffrey Holmes, Mark Hall, Eibe Frank
686&lt;/p&gt;&lt;/div&gt;
687
688
689
690&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
691
692&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
693Knowledge discovered in a database must be represented in a form that is easy to understand. Small, easy to interpret nuggets of knowledge from data are one requirement and the ability to induce them from a variety of data sources is a second. The literature is abound with classification algorithms, and in recent years with algorithms for time sequence analysis, but relatively little has been published on extracting meaningful information from problems involving continuous classes (regression).
694&lt;/p&gt;&lt;/div&gt;
695
696
697
698&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
699
700&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
701
702&lt;/p&gt;&lt;/div&gt;
703
704
705
706&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
707
708&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
709Model trees-decision trees with linear models at the leaf nodes-have recently emerged as an accurate method for numeric prediction that produces understandable models. However, it is well known that decision lists-ordered sets of If-Then rules-have the potential to be more compact and therefore more understandable than their tree counterparts.
710&lt;/p&gt;&lt;/div&gt;
711
712
713
714&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
715
716&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
717
718&lt;/p&gt;&lt;/div&gt;
719
720
721
722&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
723
724&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
725In this paper we present an algorithm for inducing simple, yet accurate rule sets from model trees. The algorithm works by repeatedly building model trees and selecting the best rule at each iteration. It produces rule sets that are, on the whole, as accurate but smaller than the model tree constructed from the entire dataset. Experimental results for various heuristics which attempt to find a compromise between rule accuracy and rule coverage are reported. We also show empirically that our method produces more accurate and smaller rule sets than the commercial state-of-the-art rule learning system Cubist.
726&lt;/p&gt;&lt;/div&gt;
727
728
729
730&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
731
732&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
733
734&lt;/p&gt;&lt;/div&gt;
735
736
737
738&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
739
740&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
741
742&lt;/p&gt;&lt;/div&gt;
743
744
745
746&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
747
748&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
74999/3
750&lt;/p&gt;&lt;/div&gt;
751
752
753
754&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
755
756&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
757A diagnostic tool for tree based supervised classification learning algorithms
758&lt;/p&gt;&lt;/div&gt;
759
760
761
762&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
763
764&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
765Leonard Trigg, Geoffrey Holmes
766&lt;/p&gt;&lt;/div&gt;
767
768
769
770&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
771
772&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
773The process of developing applications of machine learning and data mining that employ supervised classification algorithms includes the important step of knowledge verification. Interpretable output is presented to a user so that they can verify that the knowledge contained in the output makes sense for the given application. As the development of an application is an iterative process it is quite likely that a user would wish to compare models constructed at various times or stages.
774&lt;/p&gt;&lt;/div&gt;
775
776
777
778&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
779
780&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
781
782&lt;/p&gt;&lt;/div&gt;
783
784
785
786&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
787
788&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
789One crucial stage where comparison of models is important is when the accuracy of a model is being estimated, typically using some form of cross-validation. This stage is used to establish an estimate of how well a model will perform on unseen data. This is vital information to present to a user, but it is also important to show the degree of variation between models obtained from the entire dataset and models obtained during cross-validation. In this way it can be verified that the cross-validation models are at least structurally aligned with the model garnered from the entire dataset.
790&lt;/p&gt;&lt;/div&gt;
791
792
793
794&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
795
796&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
797
798&lt;/p&gt;&lt;/div&gt;
799
800
801
802&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
803
804&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
805This paper presents a diagnostic tool for the comparison of tree-based supervised classification models. The method is adapted from work on approximate tree matching and applied to decision trees. The tool is described together with experimental results on standard datasets.
806&lt;/p&gt;&lt;/div&gt;
807
808
809
810&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
811
812&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
813
814&lt;/p&gt;&lt;/div&gt;
815
816
817
818&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
819
820&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
821
822&lt;/p&gt;&lt;/div&gt;
823
824
825
826&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
827
828&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
82999/4
830&lt;/p&gt;&lt;/div&gt;
831
832
833
834&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
835
836&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
837Feature selection for discrete and numeric class machine learning
838&lt;/p&gt;&lt;/div&gt;
839
840
841
842&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
843
844&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
845Mark A. Hall
846&lt;/p&gt;&lt;/div&gt;
847
848
849
850&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
851
852&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
853Algorithms for feature selection fall into two broad categories: &amp;lt;I&amp;gt;wrappers&amp;lt;/I&amp;gt;use the learning algorithm itself to evaluate the usefulness of features, while &amp;lt;I&amp;gt;filters&amp;lt;/I&amp;gt;evaluate features according to heuristics based on general characteristics of the data. For application to large databases, filters have proven to be more practical than wrappers because they are much faster. However, most existing filter algorithms only work with discrete classification problems.
854&lt;/p&gt;&lt;/div&gt;
855
856
857
858&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
859
860&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
861
862&lt;/p&gt;&lt;/div&gt;
863
864
865
866&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
867
868&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
869This paper describes a fast, correlation-based filter algorithm that can be applied to continuous and discrete problems. Experiments using the new method as a preprocessing step for naïve Bayes, instance-based learning, decision trees, locally weighted regression, and model trees show it to be an effective feature selector- it reduces the data in dimensionality by more than sixty percent in most cases without negatively affecting accuracy. Also, decision and model trees built from the pre-processed data are often significantly smaller.
870&lt;/p&gt;&lt;/div&gt;
871
872
873
874&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
875
876&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
877
878&lt;/p&gt;&lt;/div&gt;
879
880
881
882&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
883
884&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
885
886&lt;/p&gt;&lt;/div&gt;
887
888
889
890&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
891
892&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
89399/5
894&lt;/p&gt;&lt;/div&gt;
895
896
897
898&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
899
900&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
901Browsing tree structures
902&lt;/p&gt;&lt;/div&gt;
903
904
905
906&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
907
908&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
909Mark Apperley, Robert Spence, Stephen Hodge, Michael Chester
910&lt;/p&gt;&lt;/div&gt;
911
912
913
914&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
915
916&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
917Graphic representations of tree structures are notoriously difficult to create, display, and interpret, particularly when the volume of information they contain, and hence the number of nodes, is large. The problem of interactively browsing information held in tree structures is examined, and the implementation of an innovative tree browser described. This browser is based on distortion-oriented display techniques and intuitive direct manipulation interaction. The tree layout is automatically generated, but the location and extent of detail shown is controlled by the user. It is suggested that these techniques could be extended to the browsing of more general networks.
918&lt;/p&gt;&lt;/div&gt;
919
920
921
922&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
923
924&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
925
926&lt;/p&gt;&lt;/div&gt;
927
928
929
930&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
931
932&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
93399/6
934&lt;/p&gt;&lt;/div&gt;
935
936
937
938&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
939
940&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
941Facilitating multiple copy/past operations
942&lt;/p&gt;&lt;/div&gt;
943
944
945
946&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
947
948&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
949Mark Apperley, Jay Baker, Dale Fletcher, Bill Rogers
950&lt;/p&gt;&lt;/div&gt;
951
952
953
954&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
955
956&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
957Copy and paste, or cut and paste, using a clipboard or paste buffer has long been the principle facility provided to users for transferring data between and within GUI applications. We argue that this mechanism can be clumsy in circumstances where several pieces of information must be moved systematically. In two situations - extraction of data fields from unstructured data found in a directed search process, and reorganisation of computer program source text - we present alternative, more natural, user interface facilities to make the task less onerous, and to provide improved visual feedback during the operation.
958&lt;/p&gt;&lt;/div&gt;
959
960
961
962&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
963
964&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
965
966&lt;/p&gt;&lt;/div&gt;
967
968
969
970&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
971
972&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
973For the data extraction task we introduce the Stretchable Selection Tool, a semi-transparent overlay augmenting the mouse pointer to automate paste operations and provide information to prompt the user. We describe a prototype implementation that functions in a collaborative software environment, allowing users to cooperate on a multiple copy/paste operation. For text reorganisation, we present an extension to Emacs, providing similar functionality, but without the collaborative features.
974&lt;/p&gt;&lt;/div&gt;
975
976
977
978&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
979
980&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
981
982&lt;/p&gt;&lt;/div&gt;
983
984
985
986&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
987
988&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
98999/7
990&lt;/p&gt;&lt;/div&gt;
991
992
993
994&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
995
996&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
997Automating iterative tasks with programming by demonstration: a user evaluation
998&lt;/p&gt;&lt;/div&gt;
999
1000
1001
1002&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1003
1004&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1005Gordon W. Paynter, Ian H. Witten
1006&lt;/p&gt;&lt;/div&gt;
1007
1008
1009
1010&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1011
1012&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1013Computer users often face iterative tasks that cannot be automated using the tools and aggregation techniques provided by their application program: they end up performing the iteration by hand, repeating user interface actions over and over again. We have implemented an agent, called Familiar, that can be taught to perform iterative tasks using programming by demonstration (PBD). Unlike other PBD systems, it is domain independent and works with unmodified, widely-used, applications in a popular operating system. In a formal evaluation, we found that users quickly learned to use the agent to automate iterative tasks. Generally, the participants preferred to use multiple selection where possible, but could and did use PBD in situations involving iteration over many commands, or when other techniques were unavailable.
1014&lt;/p&gt;&lt;/div&gt;
1015
1016
1017
1018&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1019
1020&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1021
1022&lt;/p&gt;&lt;/div&gt;
1023
1024
1025
1026&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1027
1028&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
102999/8
1030&lt;/p&gt;&lt;/div&gt;
1031
1032
1033
1034&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1035
1036&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1037A survey of software requirements specification practices in the New Zealand software industry
1038&lt;/p&gt;&lt;/div&gt;
1039
1040
1041
1042&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1043
1044&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1045Lindsay Groves, Ray Nickson, Greg Reeve, Steve Reeves, Mark Utting
1046&lt;/p&gt;&lt;/div&gt;
1047
1048
1049
1050&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1051
1052&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1053We report on the software development techniques used in the New Zealand software industry, paying particular attention to requirements gathering. We surveyed a selection of software companies with a general questionnaire and then conducted in-depth interviews with four companies. Our results show a wide variety in the kinds of companies undertaking software development, employing a wide range of software development techniques. Although our data are not sufficiently detailed to draw statistically significant conclusions, it appears that larger software development groups typically have more well-defined software development processes, spend proportionally more time on requirements gathering, and follow more rigorous testing regimes.
1054&lt;/p&gt;&lt;/div&gt;
1055
1056
1057
1058&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1059
1060&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1061
1062&lt;/p&gt;&lt;/div&gt;
1063
1064
1065
1066&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1067
1068&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
106999/9
1070&lt;/p&gt;&lt;/div&gt;
1071
1072
1073
1074&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1075
1076&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1077The LRU*WWW proxy cache document replacement algorithm
1078&lt;/p&gt;&lt;/div&gt;
1079
1080
1081
1082&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1083
1084&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1085Chung-yi Chang, Tony McGregor, Geoffrey Holmes
1086&lt;/p&gt;&lt;/div&gt;
1087
1088
1089
1090&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1091
1092&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1093Obtaining good performance from WWW proxy caches is critically dependent on the document replacement policy used by the proxy. This paper validates the work of other authors by reproducing their studies of proxy cache document replacement algorithms. From this basis a cross-trace study is mounted. This demonstrates that the performance of most document replacement algorithms is dependent on the type of workload that they are presented with. Finally we propose a new algorithm, LRU*, that consistently performs well across all our traces.
1094&lt;/p&gt;&lt;/div&gt;
1095
1096
1097
1098&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1099
1100&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1101
1102&lt;/p&gt;&lt;/div&gt;
1103
1104
1105
1106&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1107
1108&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
110999/10
1110&lt;/p&gt;&lt;/div&gt;
1111
1112
1113
1114&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1115
1116&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1117Reduced-error pruning with significance tests
1118&lt;/p&gt;&lt;/div&gt;
1119
1120
1121
1122&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1123
1124&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1125Eibe Frank, Ian H. Witten
1126&lt;/p&gt;&lt;/div&gt;
1127
1128
1129
1130&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1131
1132&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1133When building classification models, it is common practice to prune them to counter spurious effects of the training data: this often improves performance and reduces model size. &amp;quot;Reduced-error pruning&amp;quot; is a fast pruning procedure for decision trees that is known to produce small and accurate trees. Apart from the data from which the tree is grown, it uses an independent &amp;quot;pruning&amp;quot; set, and pruning decisions are based on the model's error rate on this fresh data. Recently it has been observed that reduced-error pruning overfits the pruning data, producing unnecessarily large decision trees. This paper investigates whether standard statistical significance tests can be used to counter this phenomenon.
1134&lt;/p&gt;&lt;/div&gt;
1135
1136
1137
1138&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1139
1140&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1141
1142&lt;/p&gt;&lt;/div&gt;
1143
1144
1145
1146&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1147
1148&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1149The problem of overfitting to the pruning set highlights the need for significance testing. We investigate two classes of test, &amp;quot;parametric&amp;quot; and &amp;quot;non-parametric.&amp;quot; The standard chi-squared statistic can be used both in a parametric test and as the basis for a non-parametric permutation test. In both cases it is necessary to select the significance level at which pruning is applied. We show empirically that both versions of the chi-squared test perform equally well if their significance levels are adjusted appropriately. Using a collection of standard datasets, we show that significance testing improves on standard reduced error pruning if the significance level is tailored to the particular dataset at hand using cross-validation, yielding consistently smaller trees that perform at least as well and sometimes better.
1150&lt;/p&gt;&lt;/div&gt;
1151
1152
1153
1154&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1155
1156&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1157
1158&lt;/p&gt;&lt;/div&gt;
1159
1160
1161
1162&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1163
1164&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
116599/11
1166&lt;/p&gt;&lt;/div&gt;
1167
1168
1169
1170&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1171
1172&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1173Weka: Practical machine learning tools and techniques with Java implementations
1174&lt;/p&gt;&lt;/div&gt;
1175
1176
1177
1178&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1179
1180&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1181Ian H. Witten, Eibe Frank, Len Trigg, Mark Hall, Geoffrey Holmes, Sally Jo Cunningham
1182&lt;/p&gt;&lt;/div&gt;
1183
1184
1185
1186&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1187
1188&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1189The Waikato Environment for Knowledge Analysis (Weka) is a comprehensive suite of Java class libraries that implement many state-of-the-art machine learning and data mining algorithms. Weka is freely available on the World-Wide Web and accompanies a new text on data mining [1] which documents and fully explains all the algorithms it contains. Applications written using the Weka class libraries can be run on any computer with a Web browsing capability; this allows users to apply machine learning techniques to their own data regardless of computer platform.
1190&lt;/p&gt;&lt;/div&gt;
1191
1192
1193
1194&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1195
1196&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1197
1198&lt;/p&gt;&lt;/div&gt;
1199
1200
1201
1202&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1203
1204&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
120599/12
1206&lt;/p&gt;&lt;/div&gt;
1207
1208
1209
1210&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1211
1212&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1213Pace Regression
1214&lt;/p&gt;&lt;/div&gt;
1215
1216
1217
1218&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1219
1220&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1221Yong Wang, Ian H. Witten
1222&lt;/p&gt;&lt;/div&gt;
1223
1224
1225
1226&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1227
1228&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1229This paper articulates a new method of linear regression, &amp;ldquo;pace regression&amp;rdquo;, that addresses many drawbacks of standard regression reported in the literature&amp;mdash;particularly the subset selection problem. Pace regression improves on classical ordinary least squares (OLS) regression by evaluating the effect of each variable and using a clustering analysis to improve the statistical basis for estimating their contribution to the overall regression. As well as outperforming OLS, it also outperforms&amp;mdash;in a remarkably general sense&amp;mdash;other linear modeling techniques in the literature, including subset selection procedures, which seek a reduction in dimensionality that falls out as a natural byproduct of pace regression. The paper defines six procedures that share the fundamental idea of pace regression, all of which are theoretically justified in terms of asymptotic performance. Experiments confirm the performance improvement over other techniques.
1230&lt;/p&gt;&lt;/div&gt;
1231
1232
1233
1234&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1235
1236&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1237
1238&lt;/p&gt;&lt;/div&gt;
1239
1240
1241
1242&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1243
1244&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
124599/13
1246&lt;/p&gt;&lt;/div&gt;
1247
1248
1249
1250&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1251
1252&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1253A compression-based algorithm for Chinese word segmentation
1254&lt;/p&gt;&lt;/div&gt;
1255
1256
1257
1258&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1259
1260&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1261W.J. Teahan, Yingying Wen, Rodger McNab, Ian H. Witten
1262&lt;/p&gt;&lt;/div&gt;
1263
1264
1265
1266&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1267
1268&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1269The Chinese language is written without using spaces or other word delimiters. Although a text may be thought of as a corresponding sequence of words, there is considerable ambiguity in the placement of boundaries. Interpreting a text as a sequence of words is beneficial for some information retrieval and storage tasks: for example, full-text search, word-based compression, and keyphrase extraction.
1270&lt;/p&gt;&lt;/div&gt;
1271
1272
1273
1274&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1275
1276&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1277
1278&lt;/p&gt;&lt;/div&gt;
1279
1280
1281
1282&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1283
1284&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1285We describe a scheme that infers appropriate positions for word boundaries using an adaptive language model that is standard in text compression. It is trained on a corpus of pre-segmented text, and when applied to new text, interpolates word boundaries so as to maximize the compression obtained. This simple and general method performs well with respect to specialized schemes for Chinese language segmentation.
1286&lt;/p&gt;&lt;/div&gt;
1287
1288
1289
1290&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1291
1292&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1293
1294&lt;/p&gt;&lt;/div&gt;
1295
1296
1297
1298&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1299
1300&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
130199/14
1302&lt;/p&gt;&lt;/div&gt;
1303
1304
1305
1306&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1307
1308&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1309Clustering with finite data from semi-parametric mixture distributions
1310&lt;/p&gt;&lt;/div&gt;
1311
1312
1313
1314&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1315
1316&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1317Yong Wang, Ian H. Witten
1318&lt;/p&gt;&lt;/div&gt;
1319
1320
1321
1322&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1323
1324&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1325Existing clustering methods for the semi-parametric mixture distribution perform well as the volume of data increases. However, they all suffer from a serious drawback in finite-data situations: small outlying groups of data points can be completely ignored in the clusters that are produced, no matter how far away they lie from the major clusters. This can result in unbounded loss if the loss function is sensitive to the distance between clusters.
1326&lt;/p&gt;&lt;/div&gt;
1327
1328
1329
1330&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1331
1332&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1333This paper proposes a new distance-based clustering method that overcomes the problem by avoiding global constraints. Experimental results illustrate its superiority to existing methods when small clusters are present in finite data sets; they also suggest that it is more accurate and stable than other methods even when there are no small clusters.
1334&lt;/p&gt;&lt;/div&gt;
1335
1336
1337
1338&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1339
1340&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1341
1342&lt;/p&gt;&lt;/div&gt;
1343
1344
1345
1346&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1347
1348&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
134999/15
1350&lt;/p&gt;&lt;/div&gt;
1351
1352
1353
1354&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1355
1356&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1357
1358&lt;/p&gt;&lt;/div&gt;
1359
1360
1361
1362&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1363
1364&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1365
1366&lt;/p&gt;&lt;/div&gt;
1367
1368
1369
1370&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1371
1372&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
137399/16
1374&lt;/p&gt;&lt;/div&gt;
1375
1376
1377
1378&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1379
1380&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1381The Niupepa Collection: Opening the blinds on a window to the past
1382&lt;/p&gt;&lt;/div&gt;
1383
1384
1385
1386&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1387
1388&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1389Te Taka Keegan, Sally Jo Cunningham, Mark Apperley
1390&lt;/p&gt;&lt;/div&gt;
1391
1392
1393
1394&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1395
1396&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1397This paper describes the building of a digital library collection of historic newspapers. The newspapers (&lt;i&gt;Niupepa&lt;/i&gt; in Maori), which were published in New Zealand during the period 1842 to 1933, form a unique historical record of the Maori language, and of events from an historical perspective. Images of these newspapers have been converted to digital form, electronic text extracted from these, and the collection is now being made available over the Internet as a part of the New Zealand Digital Library (NZDL) project at the University of Waikato.
1398&lt;/p&gt;&lt;/div&gt;
1399
1400
1401
1402&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1403
1404&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1405
1406&lt;/p&gt;&lt;/div&gt;
1407
1408
1409
1410&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1411
1412&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1413
1414&lt;/p&gt;&lt;/div&gt;
1415
1416
1417
1418&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1419
1420&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1421
1422&lt;/p&gt;&lt;/div&gt;
1423
1424
1425
1426&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1427
1428&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
142998/1
1430&lt;/p&gt;&lt;/div&gt;
1431
1432
1433
1434&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1435
1436&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1437Boosting trees for cost-sensitive classifications
1438&lt;/p&gt;&lt;/div&gt;
1439
1440
1441
1442&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1443
1444&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1445Kai Ming Ting, Zijian Zheng
1446&lt;/p&gt;&lt;/div&gt;
1447
1448
1449
1450&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1451
1452&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1453This paper explores two boosting techniques for cost-sensitive tree classification in the situation where misclassification costs change very often. Ideally, one would like to have only one induction, and use the induced model for different misclassification costs. Thus, it demands robustness of the induced model against cost changes. Combining multiple trees gives robust predictions against this change. We demonstrate that ordinary boosting combined with the minimum expected cost criterion to select the prediction class is a good solution under this situation. We also introduce a variant of the ordinary boosting procedure which utilizes the cost information during training. We show that the proposed technique performs better than the ordinary boosting in terms of misclassification cost. However, this technique requires to induce a set of new trees every time the cost changes. Our empirical investigation also reveals some interesting behavior of boosting decision trees for cost-sensitive classification.
1454&lt;/p&gt;&lt;/div&gt;
1455
1456
1457
1458&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1459
1460&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1461
1462&lt;/p&gt;&lt;/div&gt;
1463
1464
1465
1466&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1467
1468&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1469
1470&lt;/p&gt;&lt;/div&gt;
1471
1472
1473
1474&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1475
1476&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
147798/2
1478&lt;/p&gt;&lt;/div&gt;
1479
1480
1481
1482&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1483
1484&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1485Generating accurate rule sets without global optimization
1486&lt;/p&gt;&lt;/div&gt;
1487
1488
1489
1490&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1491
1492&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1493Eibe Frank, Ian H. Witten
1494&lt;/p&gt;&lt;/div&gt;
1495
1496
1497
1498&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1499
1500&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1501The two dominant schemes for rule-learning, C4.5 and RIPPER, both operate in two stages. First they induce an initial rule set and then they refine it using a rather complex optimization stage that discards (C4.5) or adjusts (RIPPER) individual rules to make them work better together. In contrast, this paper shows how good rule sets can be learned one rule at a time, without any need for global optimization. We present an algorithm for inferring rules by repeatedly generating partial decision trees, thus combining the two major paradigms for rule generation-creating rules from decision trees and the separate-and-conquer rule-learning technique. The algorithm is straightforward and elegant: despite this, experiments on standard datasets show that it produces rule sets that are as accurate as and of similar size to those generated by C4.5, and more accurate than RIPPER's. Moreover, it operates efficiently, and because it avoids postprocessing, does not suffer the extremely slow performance on pathological example sets for which the C4.5 method has been criticized.
1502&lt;/p&gt;&lt;/div&gt;
1503
1504
1505
1506&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1507
1508&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1509
1510&lt;/p&gt;&lt;/div&gt;
1511
1512
1513
1514&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1515
1516&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1517
1518&lt;/p&gt;&lt;/div&gt;
1519
1520
1521
1522&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1523
1524&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
152598/3
1526&lt;/p&gt;&lt;/div&gt;
1527
1528
1529
1530&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1531
1532&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1533VQuery: a graphical user interface for Boolean query Specification and dynamic result preview
1534&lt;/p&gt;&lt;/div&gt;
1535
1536
1537
1538&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1539
1540&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1541Steve Jones
1542&lt;/p&gt;&lt;/div&gt;
1543
1544
1545
1546&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1547
1548&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1549Textual query languages based on Boolean logic are common amongst the search facilities of on-line information repositories. However, there is evidence to suggest that the syntactic and semantic demands of such languages lead to user errors and adversely affect the time that it takes users to form queries. Additionally, users are faced with user interfaces to these repositories which are unresponsive and uninformative, and consequently fail to support effective query refinement. We suggest that graphical query languages, particularly Venn-like diagrams, provide a natural medium for Boolean query specification which overcomes the problems of textual query languages. Also, dynamic result previews can be seamlessly integrated with graphical query specification to increase the effectiveness of query refinements. We describe VQuery, a query interface to the New Zealand Digital Library which exploits querying by Venn diagrams and integrated query result previews.
1550&lt;/p&gt;&lt;/div&gt;
1551
1552
1553
1554&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1555
1556&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1557
1558&lt;/p&gt;&lt;/div&gt;
1559
1560
1561
1562&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1563
1564&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1565
1566&lt;/p&gt;&lt;/div&gt;
1567
1568
1569
1570&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1571
1572&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
157398/4
1574&lt;/p&gt;&lt;/div&gt;
1575
1576
1577
1578&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1579
1580&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1581Revising &amp;lt;I&amp;gt;Z&amp;lt;/I&amp;gt;: semantics and logic
1582&lt;/p&gt;&lt;/div&gt;
1583
1584
1585
1586&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1587
1588&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1589Martin C. Henson, Steve Reeves
1590&lt;/p&gt;&lt;/div&gt;
1591
1592
1593
1594&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1595
1596&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1597We introduce a simple specification logic &amp;lt;I&amp;gt;Z&amp;lt;/I&amp;gt;c comprising a logic and semantics (in &amp;lt;I&amp;gt;ZF&amp;lt;/I&amp;gt; set theory). We then provide an interpretation for (a rational reconstruction of) the specification language &amp;lt;I&amp;gt;Z&amp;lt;/I&amp;gt; within &amp;lt;I&amp;gt;Z&amp;lt;/I&amp;gt;c. As a result we obtain a sound logic for &amp;lt;I&amp;gt;Z&amp;lt;/I&amp;gt;, including the schema calculus. A consequence of our formalisation is a critique of a number of concepts used in &amp;lt;I&amp;gt;Z&amp;lt;/I&amp;gt;. We demonstrate that the complications and confusions which these concepts introduce can be avoided without compromising expressibility.
1598&lt;/p&gt;&lt;/div&gt;
1599
1600
1601
1602&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1603
1604&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1605
1606&lt;/p&gt;&lt;/div&gt;
1607
1608
1609
1610&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1611
1612&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1613
1614&lt;/p&gt;&lt;/div&gt;
1615
1616
1617
1618&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1619
1620&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
162198/5
1622&lt;/p&gt;&lt;/div&gt;
1623
1624
1625
1626&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1627
1628&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1629A logic for the schema calculus
1630&lt;/p&gt;&lt;/div&gt;
1631
1632
1633
1634&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1635
1636&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1637Martin C. Henson, Steve Reeves
1638&lt;/p&gt;&lt;/div&gt;
1639
1640
1641
1642&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1643
1644&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1645In this paper we introduce and investigate a logic for the schema calculus of &amp;lt;I&amp;gt;Z&amp;lt;/I&amp;gt;. The schema calculus is arguably the reason for &amp;lt;I&amp;gt;Z&amp;lt;/I&amp;gt;'s popularity but so far no true calculus (a sound system of rules for reasoning about schema expressions) has been given. Presentations thus far have either failed to provide a calculus (e.g. the draft standard [3]) or have fallen back on informal descriptions at a syntactic level (most text books e.g. [7[). Once the calculus is established we introduce a derived equational logic which enables us to formalise properly the informal notations of schema expression equality to be found in the literature.
1646&lt;/p&gt;&lt;/div&gt;
1647
1648
1649
1650&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1651
1652&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1653
1654&lt;/p&gt;&lt;/div&gt;
1655
1656
1657
1658&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1659
1660&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1661
1662&lt;/p&gt;&lt;/div&gt;
1663
1664
1665
1666&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1667
1668&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
166998/6
1670&lt;/p&gt;&lt;/div&gt;
1671
1672
1673
1674&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1675
1676&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1677New foundations for &amp;lt;I&amp;gt;Z&amp;lt;/I&amp;gt;
1678&lt;/p&gt;&lt;/div&gt;
1679
1680
1681
1682&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1683
1684&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1685Martin C. Henson, Steve Reeves
1686&lt;/p&gt;&lt;/div&gt;
1687
1688
1689
1690&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1691
1692&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1693We provide a constructive and intensional interpretation for the specification language &amp;lt;I&amp;gt;Z&amp;lt;/I&amp;gt; in a theory of operations and kinds &amp;lt;I&amp;gt;T&amp;lt;/I&amp;gt;. The motivation is to facilitate the development of an integrated approach to program construction. We illustrate the new foundations for &amp;lt;I&amp;gt;Z&amp;lt;/I&amp;gt; with examples.
1694&lt;/p&gt;&lt;/div&gt;
1695
1696
1697
1698&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1699
1700&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1701
1702&lt;/p&gt;&lt;/div&gt;
1703
1704
1705
1706&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1707
1708&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1709
1710&lt;/p&gt;&lt;/div&gt;
1711
1712
1713
1714&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1715
1716&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
171798/7
1718&lt;/p&gt;&lt;/div&gt;
1719
1720
1721
1722&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1723
1724&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1725Predicting apple bruising relationships using machine learning
1726&lt;/p&gt;&lt;/div&gt;
1727
1728
1729
1730&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1731
1732&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1733G. Holmes, S.J. Cunningham, B.T. Dela Rue, A.F. Bollen
1734&lt;/p&gt;&lt;/div&gt;
1735
1736
1737
1738&lt;p&gt;&lt;div name=&quot;Body Text&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1739
1740&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1741Many models have been used to describe the influence of internal or external factors on apple bruising. Few of these have addressed the application of derived relationships to the evaluation of commercial operations. From an industry perspective, a model must enable fruit to be rejected on the basis of a commercially significant bruise and must also accurately quantify the effects of various combinations of input features (such as cultivar, maturity, size, and so on) on bruise prediction. Input features must in turn have characteristics which are measurable commercially; for example, the measure of force should be impact energy rather than energy absorbed. Further, as the commercial criteria for acceptable damage levels change, the model should be versatile enough to regenerate new bruise thresholds from existing data.
1742&lt;/p&gt;&lt;/div&gt;
1743
1744
1745
1746&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1747
1748&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1749
1750&lt;/p&gt;&lt;/div&gt;
1751
1752
1753
1754&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1755
1756&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1757Machine learning is a burgeoning technology with a vast range of potential applications particularly in agriculture where large amounts of data can be readily collected [1]. The main advantage of using a machine learning method in an application is that the models built for prediction can be viewed and understood by the owner of the data who is in a position to determine the usefulness of the model, an essential component in a commercial environment.
1758&lt;/p&gt;&lt;/div&gt;
1759
1760
1761
1762&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1763
1764&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1765
1766&lt;/p&gt;&lt;/div&gt;
1767
1768
1769
1770&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1771
1772&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1773
1774&lt;/p&gt;&lt;/div&gt;
1775
1776
1777
1778&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1779
1780&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
178198/8
1782&lt;/p&gt;&lt;/div&gt;
1783
1784
1785
1786&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1787
1788&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1789An evaluation of passage-level indexing strategies for a technical report archive
1790&lt;/p&gt;&lt;/div&gt;
1791
1792
1793
1794&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1795
1796&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1797Michael Williams
1798&lt;/p&gt;&lt;/div&gt;
1799
1800
1801
1802&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1803
1804&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1805Past research has shown that using evidence from document passages rather than complete documents is an effective way of improving the precision of full-text database searches. However, passage-level indexing has yet to be widely adopted for commercial or online databases.
1806&lt;/p&gt;&lt;/div&gt;
1807
1808
1809
1810&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1811
1812&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1813
1814&lt;/p&gt;&lt;/div&gt;
1815
1816
1817
1818&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1819
1820&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1821This paper reports on experiments designed to test the efficacy of passage-level indexing with a particular collection of a full-text online database, the New Zealand Digital Library. Discourse passages and word-window passages are used for the indexing process. Both ranked and Boolean searching are used to test the resulting indexes.
1822&lt;/p&gt;&lt;/div&gt;
1823
1824
1825
1826&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1827
1828&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1829
1830&lt;/p&gt;&lt;/div&gt;
1831
1832
1833
1834&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1835
1836&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1837Overlapping window passages are shown to offer the best retrieval performance with both ranked and Boolean queries. Modifications may be necessary to the term weighting methodology in order to ensure optimal ranked query performance.
1838&lt;/p&gt;&lt;/div&gt;
1839
1840
1841
1842&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1843
1844&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1845
1846&lt;/p&gt;&lt;/div&gt;
1847
1848
1849
1850&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1851
1852&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1853
1854&lt;/p&gt;&lt;/div&gt;
1855
1856
1857
1858&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1859
1860&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
186198/9
1862&lt;/p&gt;&lt;/div&gt;
1863
1864
1865
1866&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1867
1868&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1869Managing multiple collections, multiple languages, and multiple media in a distributed digital library
1870&lt;/p&gt;&lt;/div&gt;
1871
1872
1873
1874&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1875
1876&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1877Ian H. Witten, Rodger McNab, Steve Jones, Sally Jo Cunningham, David Bainbridge, Mark Apperley
1878&lt;/p&gt;&lt;/div&gt;
1879
1880
1881
1882&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1883
1884&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1885Managing the organizational and software complexity of a comprehensive digital library presents a significant challenge. Different library collections each have their own distinctive features. Different presentation languages have structural implications such as left-to-right writing order and text-only interfaces for the visually impaired. Different media involve different file formats, and-more importantly-radically different search strategies are required for non-textual media. In a distributed library, new collections can appear asynchronously on servers in different parts of the world. And as searching interfaces mature from the command-line era exemplified by current Web search engines into the age of reactive visual interfaces, experimental new interfaces must be developed, supported, and tested. This paper describes our experience, gained from operating a substantial digital library service over several years, in solving these problems by designing an appropriate software architecture.
1886&lt;/p&gt;&lt;/div&gt;
1887
1888
1889
1890&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1891
1892&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1893
1894&lt;/p&gt;&lt;/div&gt;
1895
1896
1897
1898&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1899
1900&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1901
1902&lt;/p&gt;&lt;/div&gt;
1903
1904
1905
1906&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1907
1908&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
190998/10
1910&lt;/p&gt;&lt;/div&gt;
1911
1912
1913
1914&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1915
1916&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1917Experiences with a weighted decision tree learner
1918&lt;/p&gt;&lt;/div&gt;
1919
1920
1921
1922&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1923
1924&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1925John G. Cleary, Leonard E. Trigg
1926&lt;/p&gt;&lt;/div&gt;
1927
1928
1929
1930&lt;p&gt;&lt;div name=&quot;Body Text&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1931
1932&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1933Machine learning algorithms for inferring decision trees typically choose a single &amp;ldquo;best&amp;rdquo; tree to describe the training data. Recent research has shown that classification performance can be significantly improved by voting predictions of multiple, independently produced decision trees. This paper describes an algorithm, OB1, that makes a weighted sum over many possible models. We describe one instance of OB1, that includes &amp;lt;I&amp;gt;all&amp;lt;/I&amp;gt; possible decision trees as well as naïve Bayesian models. OB1 is compared with a number of other decision tree and instance based learning alogrithms on some of the data sets from the UCI repository. Both an information gain and an accuracy measure are used for the comparison. On the information gain measure OB1 performs significantly better than all the other algorithms. On the accuracy measure it is significantly better than all the algorithms except naïve Bayes which performs comparably to OB1.
1934&lt;/p&gt;&lt;/div&gt;
1935
1936
1937
1938&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1939
1940&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1941
1942&lt;/p&gt;&lt;/div&gt;
1943
1944
1945
1946&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1947
1948&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1949
1950&lt;/p&gt;&lt;/div&gt;
1951
1952
1953
1954&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1955
1956&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
195798/11
1958&lt;/p&gt;&lt;/div&gt;
1959
1960
1961
1962&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1963
1964&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1965An entropy gain measure of numeric prediction performance
1966&lt;/p&gt;&lt;/div&gt;
1967
1968
1969
1970&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1971
1972&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1973Leonard Trigg
1974&lt;/p&gt;&lt;/div&gt;
1975
1976
1977
1978&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1979
1980&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1981Categorical classifier performance is typically evaluated with respect to error rate, expressed as a percentage of test instances that were not correctly classified. When a classifier produces multiple classifications for a test instance, the prediction is counted as incorrect (even if the correct class was one of the predictions). Although commonly used in the literature, error rate is a coarse measure of classifier performance, as it is based only on a single prediction offered for a test instance. Since many classifiers can produce a class distribution as a prediction, we should use this to provide a better measure of how much information the classifier is extracting from the domain.
1982&lt;/p&gt;&lt;/div&gt;
1983
1984
1985
1986&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1987
1988&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1989
1990&lt;/p&gt;&lt;/div&gt;
1991
1992
1993
1994&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
1995
1996&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
1997Numeric classifiers are a relatively new development in machine learning, and as such there is no single performance measure that has become standard. Typically these machine learning schemes predict a single real number for each test instance, and the error between the predicted and actual value is used to calculate a myriad of performance measures such as correlation coefficient, root mean squared error, mean absolute error, relative absolute error, and root relative squared error. With so many performance measures it is difficult to establish an overall performance evaluation.
1998&lt;/p&gt;&lt;/div&gt;
1999
2000
2001
2002&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2003
2004&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2005
2006&lt;/p&gt;&lt;/div&gt;
2007
2008
2009
2010&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2011
2012&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2013The next section describes a performance measure for machine learning schemes that attempts to overcome the problems with current measures. In addition, the same evaluation measure is used for categorical and numeric classifier.
2014&lt;/p&gt;&lt;/div&gt;
2015
2016
2017
2018&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2019
2020&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2021
2022&lt;/p&gt;&lt;/div&gt;
2023
2024
2025
2026&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2027
2028&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2029
2030&lt;/p&gt;&lt;/div&gt;
2031
2032
2033
2034&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2035
2036&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2037
2038&lt;/p&gt;&lt;/div&gt;
2039
2040
2041
2042&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2043
2044&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
204598/12
2046&lt;/p&gt;&lt;/div&gt;
2047
2048
2049
2050&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2051
2052&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2053Proceedings of CBISE '98 CaiSE*98 Workshop on Component Based Information Systems Engineering
2054&lt;/p&gt;&lt;/div&gt;
2055
2056
2057
2058&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2059
2060&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2061Edited by John Grundy
2062&lt;/p&gt;&lt;/div&gt;
2063
2064
2065
2066&lt;p&gt;&lt;div name=&quot;Body Text&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2067
2068&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2069Component-based information systems development is an area of research and practice of increasing importance. Information Systems developers have realised that traditional approaches to IS engineering produce monolithic, difficult to maintain, difficult to reuse systems. In contrast, the use of software components, which embody data, functionality and well-specified and understood interfaces, makes interoperable, distributed and highly reusable IS components feasible. Component-based approaches to IS engineering can be used at strategic and organisational levels, to model business processes and whole IS architectures, in development methods which utilise component-based models during analysis and design, and in system implementation. Reusable components can allow end users to compose and configure their own Information Systems, possibly from a range of suppliers, and to more tightly couple their organisational workflows with their IS support.
2070&lt;/p&gt;&lt;/div&gt;
2071
2072
2073
2074&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2075
2076&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2077
2078&lt;/p&gt;&lt;/div&gt;
2079
2080
2081
2082&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2083
2084&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2085This workshop proceedings contains a range of papers addressing one or more of the above issues relating to the use of component models for IS development. All of these papers were refereed by at least two members of an international workshop committee comprising industry and academic researchers and users of component technologies. Strategic uses of components are addressed in the first three papers, while the following three address uses of components for systems design and workflow management. Systems development using components, and the provision of environments for component management are addressed in the following group of five papers. The last three papers in this proceedings address component management and analysis techniques.
2086&lt;/p&gt;&lt;/div&gt;
2087
2088
2089
2090&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2091
2092&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2093
2094&lt;/p&gt;&lt;/div&gt;
2095
2096
2097
2098&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2099
2100&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2101All of these papers provide new insights into the many varied uses of component technology for IS engineering. I hope you find them as interesting and useful as I have when collating this proceedings and organising the workshop.
2102&lt;/p&gt;&lt;/div&gt;
2103
2104
2105
2106&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2107
2108&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2109
2110&lt;/p&gt;&lt;/div&gt;
2111
2112
2113
2114&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2115
2116&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2117
2118&lt;/p&gt;&lt;/div&gt;
2119
2120
2121
2122&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2123
2124&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
212598/13
2126&lt;/p&gt;&lt;/div&gt;
2127
2128
2129
2130&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2131
2132&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2133An analysis of usage of a digital library
2134&lt;/p&gt;&lt;/div&gt;
2135
2136
2137
2138&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2139
2140&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2141Steve Jones, Sally Jo Cunningham, Rodger McNab
2142&lt;/p&gt;&lt;/div&gt;
2143
2144
2145
2146&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2147
2148&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2149As experimental digital library testbeds gain wider acceptance and develop significant user bases, it becomes important to investigate the ways in which users interact with the systems in practice. Transaction logs are one source of usage information, and the information on user behaviour can be culled from them both automatically (through calculation of summary statistics) and manually (by examining query strings for semantic clues on search motivations and searching strategy). We conduct a transaction log analysis on user activity in the Computer Science Technical Reports Collection of the New Zealand Digital Library, and report insights gained and identify resulting search interface design issues.
2150&lt;/p&gt;&lt;/div&gt;
2151
2152
2153
2154&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2155
2156&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2157
2158&lt;/p&gt;&lt;/div&gt;
2159
2160
2161
2162&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2163
2164&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2165
2166&lt;/p&gt;&lt;/div&gt;
2167
2168
2169
2170&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2171
2172&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
217398/14
2174&lt;/p&gt;&lt;/div&gt;
2175
2176
2177
2178&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2179
2180&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2181Measuring ATM traffic: final report for New Zealand Telecom
2182&lt;/p&gt;&lt;/div&gt;
2183
2184
2185
2186&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2187
2188&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2189John Cleary, Ian Graham, Murray Pearson, Tony McGregor
2190&lt;/p&gt;&lt;/div&gt;
2191
2192
2193
2194&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2195
2196&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2197The report describes the development of a low-cost ATM monitoring system, hosted by a standard PC. The monitor can be used remotely returning information on ATM traffic flows to a central site. The monitor is interfaces to a GPS timing receiver, which provides an absolute time accuracy of better than 1 usec. By monitoring the same traffic flow at different points in a network it is possible to measure cell delay and delay variation in real time, and with existing traffic. The monitoring system characterises cells by a CRC calculated over the cell payload, thus special measurement cells are not required. Delays in both local area and wide-area networks have been measured using this system. It is possible to measure delay in a network that is not end-to-end ATM, as long as some cells remain identical at the entry and exit points. Examples are given of traffic and delay measurements in both wide and local area network systems, including delays measured over the Internet from Canada to New Zealand.
2198&lt;/p&gt;&lt;/div&gt;
2199
2200
2201
2202&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2203
2204&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2205
2206&lt;/p&gt;&lt;/div&gt;
2207
2208
2209
2210&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2211
2212&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2213
2214&lt;/p&gt;&lt;/div&gt;
2215
2216
2217
2218&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2219
2220&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2221
2222&lt;/p&gt;&lt;/div&gt;
2223
2224
2225
2226&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2227
2228&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
222998/15
2230&lt;/p&gt;&lt;/div&gt;
2231
2232
2233
2234&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2235
2236&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2237Despite its simplicity, the naïve Bayes learning scheme performs well on most classification tasks, and is often significantly more accurate than more sophisticated methods. Although the probability estimates that it produces can be inaccurate, it often assigns maximum probability to the correct class. This suggests that its good performance might be restricted to situations where the output is categorical. It is therefore interesting to see how it performs in domains where the predicted value is numeric, because in this case, predictions are more sensitive to inaccurate probability estimates.&amp;lt;P&amp;gt;
2238&lt;/p&gt;&lt;/div&gt;
2239
2240
2241
2242&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2243
2244&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2245
2246&lt;/p&gt;&lt;/div&gt;
2247
2248
2249
2250&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2251
2252&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2253This paper shows how to apply the naïve Bayes methodology to numeric prediction (i.e. regression) tasks, and compares it to linear regression, instance-based learning, and a method that produces &amp;ldquo;model trees&amp;rdquo;-decision trees with linear regression functions at the leaves. Although we exhibit an artificial dataset for which naïve Bayes is the method of choice, on real-world datasets it is almost uniformly worse than model trees. The comparison with linear regression depends on the error measure: for one measure naïve Bayes performs similarly, for another it is worse. Compared to instance-based learning, it performs similarly with respect to both measures. These results indicate that the simplistic statistical assumption that naïve Bayes makes is indeed more restrictive for regression than for classification.
2254&lt;/p&gt;&lt;/div&gt;
2255
2256
2257
2258&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2259
2260&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2261
2262&lt;/p&gt;&lt;/div&gt;
2263
2264
2265
2266&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2267
2268&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
226998/16
2270&lt;/p&gt;&lt;/div&gt;
2271
2272
2273
2274&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2275
2276&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2277Link as you type: using key phrases for automated dynamic link generation
2278&lt;/p&gt;&lt;/div&gt;
2279
2280
2281
2282&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2283
2284&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2285Steve Jones
2286&lt;/p&gt;&lt;/div&gt;
2287
2288
2289
2290&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2291
2292&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2293When documents are collected together from diverse sources they are unlikely to contain useful hypertext links to support browsing amongst them. For large collections of thousands of documents it is prohibitively resource intensive to manually insert links into each document. Users of such collections may wish to relate documents within them to text that they are themselves generating. This process, often involving keyword searching, distracts from the authoring process and results in material related to query terms but not necessarily to the author's document. Query terms that are effective in one collection might not be so in another. We have developed Phrasier, a system that integrates authoring (of text and hyperlinks), browsing, querying and reading in support of information retrieval activities. Phrasier exploits key phrases which are automatically extracted from documents in a collection, and uses them as link anchors and to identify candidate destinations for hyperlinks. This system suggests links into existing collections for purposes of authoring and retrieval of related information, creates links between documents in a collection and provides supportive document and link overviews.
2294&lt;/p&gt;&lt;/div&gt;
2295
2296
2297
2298&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2299
2300&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2301
2302&lt;/p&gt;&lt;/div&gt;
2303
2304
2305
2306&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2307
2308&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2309
2310&lt;/p&gt;&lt;/div&gt;
2311
2312
2313
2314&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2315
2316&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
231798/17
2318&lt;/p&gt;&lt;/div&gt;
2319
2320
2321
2322&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2323
2324&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2325Melody based tune retrieval over the World Wide Web
2326&lt;/p&gt;&lt;/div&gt;
2327
2328
2329
2330&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2331
2332&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2333David Bainbridge, Rodger J. McNab, Lloyd A. Smith
2334&lt;/p&gt;&lt;/div&gt;
2335
2336
2337
2338&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2339
2340&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2341In this paper we describe the steps taken to develop a Web-based version of an existing stand-alone, single-user digital library application for melodical searching of a collection of music. For the three key components: input, searching, and output, we assess the suitability of various Web-based strategies that deal with the now distributed software architecture and explain the decisions we made. The resulting melody indexing service, known as MELDEX, has been in operation for one year, and the feed-back we have received has been favorable.
2342&lt;/p&gt;&lt;/div&gt;
2343
2344
2345
2346&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2347
2348&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2349
2350&lt;/p&gt;&lt;/div&gt;
2351
2352
2353
2354&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2355
2356&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
235798/18
2358&lt;/p&gt;&lt;/div&gt;
2359
2360
2361
2362&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2363
2364&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2365Making oral history accessible over the World Wide Web
2366&lt;/p&gt;&lt;/div&gt;
2367
2368
2369
2370&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2371
2372&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2373David Bainbridge, Sally Jo Cunningham
2374&lt;/p&gt;&lt;/div&gt;
2375
2376
2377
2378&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2379
2380&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2381We describe a multimedia, WWW-based oral history collection constructed from off-the-shelf or publicly available software. The source materials for the collection include audio tapes of interviews and summary transcripts of each interview, as well as photographs illustrating episodes mentioned in the tapes. Sections of the transcripts are manually matched to associated segments of the tapes, and the tapes are digitized. Users search a full-text retrieval system based on the text transcripts to retrieve relevant transcript sections and their associated audio recordings and photographs. It is also possible to search for photos by matching text queries against text descriptions of the photos in the collection, where the located photos link back to their respective interview transcript and audio recordings.
2382&lt;/p&gt;&lt;/div&gt;
2383
2384
2385
2386&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2387
2388&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2389
2390&lt;/p&gt;&lt;/div&gt;
2391
2392
2393
2394&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2395
2396&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2397
2398&lt;/p&gt;&lt;/div&gt;
2399
2400
2401
2402&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2403
2404&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2405
2406&lt;/p&gt;&lt;/div&gt;
2407
2408
2409
2410&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2411
2412&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2413
2414&lt;/p&gt;&lt;/div&gt;
2415
2416
2417
2418&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2419
2420&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2421&lt;b&gt;1997&lt;/b&gt;
2422&lt;/p&gt;&lt;/div&gt;
2423
2424
2425
2426&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2427
2428&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2429
2430&lt;/p&gt;&lt;/div&gt;
2431
2432
2433
2434&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2435
2436&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
243797/1
2438&lt;/p&gt;&lt;/div&gt;
2439
2440
2441
2442&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2443
2444&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2445A dynamic and flexible representation of social relationships in CSCW
2446&lt;/p&gt;&lt;/div&gt;
2447
2448
2449
2450&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2451
2452&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2453Steve Jones, Steve Marsh
2454&lt;/p&gt;&lt;/div&gt;
2455
2456
2457
2458&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2459
2460&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2461CSCW system designers lack effective support in addressing the social issues and interpersonal relationships which are linked with the use of CSCW systems. We present a formal description of trust to support CSCW system designers in considering the social aspects of group work, embedding those considerations in systems and analysing computer supported group processes.
2462&lt;/p&gt;&lt;/div&gt;
2463
2464
2465
2466&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2467
2468&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2469
2470&lt;/p&gt;&lt;/div&gt;
2471
2472
2473
2474&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2475
2476&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2477We argue that trust is a critical aspect in group work, and describe what we consider to be the building blocks of trust. We then present a formal notation for the building blocks, their use in reasoning about social interactions and how they are amended over time.
2478&lt;/p&gt;&lt;/div&gt;
2479
2480
2481
2482&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2483
2484&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2485
2486&lt;/p&gt;&lt;/div&gt;
2487
2488
2489
2490&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2491
2492&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2493We then consider how the formalism may be used in practice, and present some insights from initial analysis of the behaviour of the formalism. This is followed by a description of possible amendments and extensions to the formalism. We conclude that it is possible to formalise a notion of trust and to model the formalisation by a computational mechanism.
2494&lt;/p&gt;&lt;/div&gt;
2495
2496
2497
2498&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2499
2500&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2501
2502&lt;/p&gt;&lt;/div&gt;
2503
2504
2505
2506&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2507
2508&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2509
2510&lt;/p&gt;&lt;/div&gt;
2511
2512
2513
2514&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2515
2516&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
251797/2
2518&lt;/p&gt;&lt;/div&gt;
2519
2520
2521
2522&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2523
2524&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2525Design issues for World Wide Web navigation visualisation tools
2526&lt;/p&gt;&lt;/div&gt;
2527
2528
2529
2530&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2531
2532&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2533Andy Cockburn, Steve Jones
2534&lt;/p&gt;&lt;/div&gt;
2535
2536
2537
2538&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2539
2540&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2541The World Wide Web (WWW) is a successful hypermedia information space used by millions of people, yet it suffers from many deficiencies and problems in support for navigation around its vast information space. In this paper we identify the origins of these navigation problems, namely WWW browser design, WWW page design, and WWW page description languages. Regardless of their origins, these problems are eventually represented to the user at the browser's user interface. To help overcome these problems, many tools are being developed which allow users to visualise WWW subspaces. We identify five key issues in the design and functionality of these visualisation systems: characteristics of the visual representation, the scope of the subspace representation, the mechanisms for generating the visualisation, the degree of browser independence, and the navigation support facilities. We provide a critical review of the diverse range of WWW visualisation tools with respect to these issues.
2542&lt;/p&gt;&lt;/div&gt;
2543
2544
2545
2546&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2547
2548&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2549
2550&lt;/p&gt;&lt;/div&gt;
2551
2552
2553
2554&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2555
2556&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2557
2558&lt;/p&gt;&lt;/div&gt;
2559
2560
2561
2562&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2563
2564&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
256597/3
2566&lt;/p&gt;&lt;/div&gt;
2567
2568
2569
2570&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2571
2572&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2573Stacked generalization: when does it work?
2574&lt;/p&gt;&lt;/div&gt;
2575
2576
2577
2578&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2579
2580&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2581Kai Ming Ting, Ian H. Witten
2582&lt;/p&gt;&lt;/div&gt;
2583
2584
2585
2586&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2587
2588&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2589Stacked generalization is a general method of using a high-level model to combine lower-level models to achieve greater predictive accuracy. In this paper we address two crucial issues which have been considered to be a 'black art' in classification tasks ever since the introduction of stacked generalization in 1992 by Wolpert: the type of generalizer that is suitable to derive the higher-level model, and the kind of attributes that should be used as its input.
2590&lt;/p&gt;&lt;/div&gt;
2591
2592
2593
2594&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2595
2596&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2597
2598&lt;/p&gt;&lt;/div&gt;
2599
2600
2601
2602&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2603
2604&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2605We demonstrate the effectiveness of stacked generalization for combining three different types of learning algorithms, and also for combining models of the same type derived from a single learning algorithm in a multiple-data-batches scenario. We also compare the performance of stacked generalization with published results arcing and bagging.
2606&lt;/p&gt;&lt;/div&gt;
2607
2608
2609
2610&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2611
2612&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2613
2614&lt;/p&gt;&lt;/div&gt;
2615
2616
2617
2618&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2619
2620&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2621
2622&lt;/p&gt;&lt;/div&gt;
2623
2624
2625
2626&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2627
2628&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
262997/4
2630&lt;/p&gt;&lt;/div&gt;
2631
2632
2633
2634&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2635
2636&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2637Browsing in digital libraries: a phrase-based approach
2638&lt;/p&gt;&lt;/div&gt;
2639
2640
2641
2642&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2643
2644&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2645Craig Nevill-Manning, Ian H. Witten, Gordon W. Paynter
2646&lt;/p&gt;&lt;/div&gt;
2647
2648
2649
2650&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2651
2652&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2653A key question for digital libraries is this: how should one go about becoming familiar with a digital collection, as opposed to a physical one? Digital collections generally present an appearance which is extremely opaque-a screen, typically a Web page, with no indication of what, or how much, lies beyond: whether a carefully-selected collection or a morass of worthless ephemera; whether half a dozen documents or many millions. At least physical collections occupy physical space, present a physical appearance, and exhibit tangible physical organization. When standing on the threshold of a large library one gains a sense of presence and permanence that reflects the care taken in building and maintaining the collection inside. No-one could confuse it with a dung-heap! Yet in the digital world the difference is not so palpable.
2654&lt;/p&gt;&lt;/div&gt;
2655
2656
2657
2658&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2659
2660&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2661
2662&lt;/p&gt;&lt;/div&gt;
2663
2664
2665
2666&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2667
2668&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2669
2670&lt;/p&gt;&lt;/div&gt;
2671
2672
2673
2674&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2675
2676&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2677
2678&lt;/p&gt;&lt;/div&gt;
2679
2680
2681
2682&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2683
2684&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
268597/5
2686&lt;/p&gt;&lt;/div&gt;
2687
2688
2689
2690&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2691
2692&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2693A graphical notation for the design of information visualisations
2694&lt;/p&gt;&lt;/div&gt;
2695
2696
2697
2698&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2699
2700&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2701Matthew C. Humphrey
2702&lt;/p&gt;&lt;/div&gt;
2703
2704
2705
2706&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2707
2708&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2709Visualisations are coherent, graphical expressions of complex information that enhance people's ability to communicate and reason about that information. Yet despite the importance of visualisations in helping people to understand and solve a wide variety of problems, there is a dearth of formal tools and methods for discussing, describing and designing them. Although simple visualisations, such as bar charts and scatterplots, are easily produced by modern interactive software, novel visualisations of multivariate, multirelational data must be expressed in a programming language. The Relational Visualisation Notation is a new, graphical language for designing such highly expressive visualisations that does not use programming constructs. Instead, the notation is based on relational algebra, which is widely used in database query languages, and it is supported by a suite of direct manipulation tools. This article presents the notation and examines the designs of some interesting visualisations.
2710&lt;/p&gt;&lt;/div&gt;
2711
2712
2713
2714&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2715
2716&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2717
2718&lt;/p&gt;&lt;/div&gt;
2719
2720
2721
2722&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2723
2724&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2725
2726&lt;/p&gt;&lt;/div&gt;
2727
2728
2729
2730&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2731
2732&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2733
2734&lt;/p&gt;&lt;/div&gt;
2735
2736
2737
2738&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2739
2740&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
274197/6
2742&lt;/p&gt;&lt;/div&gt;
2743
2744
2745
2746&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2747
2748&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2749Applications of machine learning in information retrieval
2750&lt;/p&gt;&lt;/div&gt;
2751
2752
2753
2754&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2755
2756&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2757Sally Jo Cunningham, James Littin, Ian H. Witten
2758&lt;/p&gt;&lt;/div&gt;
2759
2760
2761
2762&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2763
2764&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2765Information retrieval systems provide access to collections of thousands, or millions, of documents, from which, by providing an appropriate description, users can recover any one. Typically, users iteratively refine the descriptions they provide to satisfy their needs, and retrieval systems can utilize user feedback on selected documents to indicate the accuracy of the description at any stage. The style of description required from the user, and the way it is employed to search the document database, are consequences of the indexing method used for the collection. The index may take different forms, from storing keywords with links to individual documents, to clustering documents under related topics.
2766&lt;/p&gt;&lt;/div&gt;
2767
2768
2769
2770&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2771
2772&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2773
2774&lt;/p&gt;&lt;/div&gt;
2775
2776
2777
2778&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2779
2780&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2781
2782&lt;/p&gt;&lt;/div&gt;
2783
2784
2785
2786&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2787
2788&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2789
2790&lt;/p&gt;&lt;/div&gt;
2791
2792
2793
2794&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2795
2796&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
279797/7
2798&lt;/p&gt;&lt;/div&gt;
2799
2800
2801
2802&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2803
2804&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2805Computer concepts without computers: a first course in computer science
2806&lt;/p&gt;&lt;/div&gt;
2807
2808
2809
2810&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2811
2812&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2813Geoffrey Holmes, Tony C. Smith, William J. Rogers
2814&lt;/p&gt;&lt;/div&gt;
2815
2816
2817
2818&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2819
2820&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2821While some institutions seek to make CS1 curricula more enjoyable by incorporating specialised educational software [1] or by setting more enjoyable programming assignments [2], we have joined the growing number of Computer Science departments that seek to improve the quality of the CS1 experience by focusing student attention away from the computer monitor [3,4]. Sophisticated computing concepts usually reserved for senior level courses are presented in a &amp;lt;I&amp;gt;popular science&amp;lt;/I&amp;gt; manner, and given equal time alongside the essential introductory programming material. By exposing students to a broad range of specific computational problems we endeavour to make the introductory course more interesting and enjoyable, and instil in students a sense of vision for areas they might specialise in as computing majors.
2822&lt;/p&gt;&lt;/div&gt;
2823
2824
2825
2826&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2827
2828&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2829
2830&lt;/p&gt;&lt;/div&gt;
2831
2832
2833
2834&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2835
2836&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2837
2838&lt;/p&gt;&lt;/div&gt;
2839
2840
2841
2842&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2843
2844&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2845
2846&lt;/p&gt;&lt;/div&gt;
2847
2848
2849
2850&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2851
2852&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
285397/8
2854&lt;/p&gt;&lt;/div&gt;
2855
2856
2857
2858&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2859
2860&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2861A sight-singing tutor
2862&lt;/p&gt;&lt;/div&gt;
2863
2864
2865
2866&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2867
2868&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2869Lloyd A. Smith, Rodger J. McNab
2870&lt;/p&gt;&lt;/div&gt;
2871
2872
2873
2874&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2875
2876&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2877This paper describes a computer program designed to aid its users in learning to sight-sing. Sight-singing-the ability to sing music from a score without prior study-is an important skill for musicians and holds a central place in most university music curricula. Its importance to vocalists is obvious; it is also an important skill for instrumentalists and conductors because it develops the aural imagination necessary to judge how the music should sound, when played (Benward and Carr 1991). Furthermore, it is an important skill for amateur musicians, who can save a great deal of rehearsal time through an ability to sing music at sight.
2878&lt;/p&gt;&lt;/div&gt;
2879
2880
2881
2882&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2883
2884&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2885
2886&lt;/p&gt;&lt;/div&gt;
2887
2888
2889
2890&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2891
2892&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2893
2894&lt;/p&gt;&lt;/div&gt;
2895
2896
2897
2898&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2899
2900&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
290197/9
2902&lt;/p&gt;&lt;/div&gt;
2903
2904
2905
2906&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2907
2908&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2909Stacking bagged and dagged models
2910&lt;/p&gt;&lt;/div&gt;
2911
2912
2913
2914&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2915
2916&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2917Kai Ming Ting, I.H. Witten
2918&lt;/p&gt;&lt;/div&gt;
2919
2920
2921
2922&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2923
2924&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2925In this paper, we investigate the method of &lt;i&gt;stacked generalization&lt;/i&gt; in combining models derived from different subsets of a training dataset by a single learning algorithm, as well as different algorithms. The simplest way to combine predictions from competing models is majority vote, and the effect of the sampling regime used to generate training subsets has already been studied in this context-when bootstrap samples are used the method is called &lt;i&gt;bagging&lt;/i&gt;, and for disjoint samples we call it &lt;i&gt;dagging&lt;/i&gt;. This paper extends these studies to stacked generalization, where a learning algorithm is employed to combine the models. This yields new methods dubbed &lt;i&gt;bag-stacking&lt;/i&gt; and &lt;i&gt;dag-stacking&lt;/i&gt;.
2926&lt;/p&gt;&lt;/div&gt;
2927
2928
2929
2930&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2931
2932&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2933
2934&lt;/p&gt;&lt;/div&gt;
2935
2936
2937
2938&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2939
2940&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2941We demonstrate that bag-stacking and dag-stacking can be effective for classification tasks even when the training samples cover just a small fraction of the full dataset. In contrast to earlier bagging results, we show that bagging and bag-stacking work for stable as well as unstable learning algorithms, as do dagging and dag-stacking. We find that bag-stacking (dag-stacking) almost always has higher predictive accuracy than bagging (dagging), and we also show that bag-stacking models derived using two different algorithms is more effective than bagging.
2942&lt;/p&gt;&lt;/div&gt;
2943
2944
2945
2946&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2947
2948&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2949
2950&lt;/p&gt;&lt;/div&gt;
2951
2952
2953
2954&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2955
2956&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2957
2958&lt;/p&gt;&lt;/div&gt;
2959
2960
2961
2962&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2963
2964&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
296597/10
2966&lt;/p&gt;&lt;/div&gt;
2967
2968
2969
2970&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2971
2972&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2973Extracting text from Postscript
2974&lt;/p&gt;&lt;/div&gt;
2975
2976
2977
2978&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2979
2980&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2981Craig Nevill-Manning, Todd Reed, Ian H. Witten
2982&lt;/p&gt;&lt;/div&gt;
2983
2984
2985
2986&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2987
2988&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2989We show how to extract plain text from PostScript files. A textual scan is inadequate because PostScript interpreters can generate characters on the page that do not appear in the source file. Furthermore, word and line breaks are implicit in the graphical rendition, and must be inferred from the positioning of word fragments. We present a robust technique for extracting text and recognizing words and paragraphs. The method uses a standard PostScript interpreter but redefines several PostScript operators, and simple heuristics are employed to locate word and line breaks. The scheme has been used to create a full-text index, and plain-text versions, of 40,000 technical reports (34 Gbyte of PostScript). Other text-extraction systems are reviewed: none offer the same combination of robustness and simplicity.
2990&lt;/p&gt;&lt;/div&gt;
2991
2992
2993
2994&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
2995
2996&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
2997
2998&lt;/p&gt;&lt;/div&gt;
2999
3000
3001
3002&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3003
3004&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3005
3006&lt;/p&gt;&lt;/div&gt;
3007
3008
3009
3010&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3011
3012&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
301397/11
3014&lt;/p&gt;&lt;/div&gt;
3015
3016
3017
3018&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3019
3020&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3021Gathering and indexing rich fragments of the World Wide Web
3022&lt;/p&gt;&lt;/div&gt;
3023
3024
3025
3026&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3027
3028&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3029Geoffrey Holmes, William J Rogers
3030&lt;/p&gt;&lt;/div&gt;
3031
3032
3033
3034&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3035
3036&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3037While the World Wide Web (WWW) is an attractive option as a resource for teaching and research it does have some undesirable features. The cost of allowing students unlimited access can be high-both in money and time; students may become addicted to 'surfing' the web-exploring purely for entertainment-and jeopardise their studies. Students are likely to discover undesirable material because large scale search engines index sites regardless of their merit. Finally, the explosive growth of WWW usage means that servers and networks are often overloaded, to the extent that a student may gain a very negative view of the technology.
3038&lt;/p&gt;&lt;/div&gt;
3039
3040
3041
3042&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3043
3044&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3045
3046&lt;/p&gt;&lt;/div&gt;
3047
3048
3049
3050&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3051
3052&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3053We have developed a piece of software which attempts to address these issues by capturing rich fragments of the WWW onto local storage media. It is possible to put a collection onto CD ROM, providing portability and inexpensive storage. This enables the presentation of the WWW to distance learning students, who do not have internet access. The software interfaces to standard, commonly available web browsers, acting as a proxy server to the files stored on the local media, and provides a search engine giving full text searching capability within the collection.
3054&lt;/p&gt;&lt;/div&gt;
3055
3056
3057
3058&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3059
3060&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3061
3062&lt;/p&gt;&lt;/div&gt;
3063
3064
3065
3066&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3067
3068&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3069
3070&lt;/p&gt;&lt;/div&gt;
3071
3072
3073
3074&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3075
3076&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3077
3078&lt;/p&gt;&lt;/div&gt;
3079
3080
3081
3082&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3083
3084&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
308597/12
3086&lt;/p&gt;&lt;/div&gt;
3087
3088
3089
3090&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3091
3092&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3093Using model trees for classification
3094&lt;/p&gt;&lt;/div&gt;
3095
3096
3097
3098&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3099
3100&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3101Eibe Frank, Yong Wang, Stuart Inglis, Geoffrey Holmes, Ian H. Witten
3102&lt;/p&gt;&lt;/div&gt;
3103
3104
3105
3106&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3107
3108&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3109Model trees, which are a type of decision tree with linear regression functions at the leaves, form the basis of a recent successful technique for predicting continuous numeric values. They can be applied to classification problems by employing a standard method of transforming a classification problem into a problem of function approximation. Surprisingly, using this simple transformation the model tree inducer M5', based on Quinlan's M5, generates more accurate classifiers than the state-of-the-art decision tree learner C5.0, particularly when most of the attributes are numeric.
3110&lt;/p&gt;&lt;/div&gt;
3111
3112
3113
3114&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3115
3116&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3117
3118&lt;/p&gt;&lt;/div&gt;
3119
3120
3121
3122&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3123
3124&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3125
3126&lt;/p&gt;&lt;/div&gt;
3127
3128
3129
3130&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3131
3132&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
313397/13
3134&lt;/p&gt;&lt;/div&gt;
3135
3136
3137
3138&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3139
3140&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3141Discovering inter-attribute relationships
3142&lt;/p&gt;&lt;/div&gt;
3143
3144
3145
3146&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3147
3148&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3149Geoffrey Holmes
3150&lt;/p&gt;&lt;/div&gt;
3151
3152
3153
3154&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3155
3156&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3157It is important to discover relationships between attributes being used to predict a class attribute in supervised learning situations for two reasons. First, any such relationship will be potentially interesting to the provider of a dataset in its own right. Second, it would simplify a learning algorithm's search space, and the related irrelevant feature and subset selection problem, if the relationships were removed from datasets ahead of learning. An algorithm to discover such relationships is presented in this paper. The algorithm is described and a surprising number of inter-attribute relationships are discovered in datasets from the University of California at Irvine (UCI) repository.
3158&lt;/p&gt;&lt;/div&gt;
3159
3160
3161
3162&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3163
3164&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3165
3166&lt;/p&gt;&lt;/div&gt;
3167
3168
3169
3170&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3171
3172&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3173
3174&lt;/p&gt;&lt;/div&gt;
3175
3176
3177
3178&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3179
3180&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
318197/14
3182&lt;/p&gt;&lt;/div&gt;
3183
3184
3185
3186&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3187
3188&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3189Learning from batched data: model combination vs data combination
3190&lt;/p&gt;&lt;/div&gt;
3191
3192
3193
3194&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3195
3196&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3197Kai Ming Ting, Boon Toh Low, Ian H. Witten
3198&lt;/p&gt;&lt;/div&gt;
3199
3200
3201
3202&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3203
3204&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3205When presented with multiple batches of data, one can either combine them into a single batch before applying a machine learning procedure or learn from each batch independently and combine the resulting models. The former procedure, data combination, is straightforward; this paper investigates the latter, model combination. Given an appropriate combination method, one might expect model combination to prove superior when the data in each batch was obtained under somewhat different conditions or when different learning algorithms were used on the batches. Empirical results show that model combination often outperforms data combination even when the batches are drawn randomly from a single source of data and the same learning method is used on each. Moreover, this is not just an artifact of one particular method of combining models: it occurs with several different combination methods.
3206&lt;/p&gt;&lt;/div&gt;
3207
3208
3209
3210&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3211
3212&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3213
3214&lt;/p&gt;&lt;/div&gt;
3215
3216
3217
3218&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3219
3220&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3221We relate this phenomenon to the learning curve of the classifiers being used. Early in the learning process when the learning curve is steep there is much to gain from data combination, but later when it becomes shallow there is less to gain and model combination achieves a greater reduction in variance and hence a lower error rate.
3222&lt;/p&gt;&lt;/div&gt;
3223
3224
3225
3226&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3227
3228&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3229
3230&lt;/p&gt;&lt;/div&gt;
3231
3232
3233
3234&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3235
3236&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3237The practical implication of these results is that one should consider using model combination rather than data combination, especially when multiple batches of data for the same task are readily available. It is often superior even when the batches are drawn randomly from a single sample, and we expect its advantage to increase if genuine statistical differences between the batches exist.
3238&lt;/p&gt;&lt;/div&gt;
3239
3240
3241
3242&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3243
3244&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3245
3246&lt;/p&gt;&lt;/div&gt;
3247
3248
3249
3250&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3251
3252&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3253
3254&lt;/p&gt;&lt;/div&gt;
3255
3256
3257
3258&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3259
3260&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
326197/15
3262&lt;/p&gt;&lt;/div&gt;
3263
3264
3265
3266&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3267
3268&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3269Information seeking retrieval, reading and storing behaviour of library users
3270&lt;/p&gt;&lt;/div&gt;
3271
3272
3273
3274&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3275
3276&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3277Turner K.
3278&lt;/p&gt;&lt;/div&gt;
3279
3280
3281
3282&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3283
3284&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3285In the interest of digital libraries, it is advisable that designers be aware of the potential behaviour of the users of such a system. There are two distinct parts under investigation, the interaction between traditional libraries involving the seeking and retrieval of relevant material, and the reading and storage behaviours ensuing. Through this analysis, the findings could be incorporated into digital library facilities. There has been copious amounts of research on information seeking leading to the development of behavioural models to describe the process. Often research on the information seeking practices of individuals is based on the task and field of study. The information seeking model, presented by Ellis et al. (1993), characterises the format of this study where it is used to compare various research on the information seeking practices of groups of people (from academics to professionals). It is found that, although researchers do make use of library facilities, they tend to rely heavily on their own collections and primarily use the library as a source for previously identified information, browsing and interloan. It was found that there are significant differences in user behaviour between the groups analysed. When looking at the reading and storage of material it was hard to draw conclusions, due to the lack of substantial research and information on the topic. However, through the use of reading strategies, a general idea on how readers behave can be developed. Designers of digital libraries can benefit from the guidelines presented here to better understand their audience.
3286&lt;/p&gt;&lt;/div&gt;
3287
3288
3289
3290&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3291
3292&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3293
3294&lt;/p&gt;&lt;/div&gt;
3295
3296
3297
3298&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3299
3300&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3301
3302&lt;/p&gt;&lt;/div&gt;
3303
3304
3305
3306&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3307
3308&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
330997/16
3310&lt;/p&gt;&lt;/div&gt;
3311
3312
3313
3314&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3315
3316&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3317Proceeding of the INTERACT97 Combined Workshop on CSCW in HCI-Worldwide
3318&lt;/p&gt;&lt;/div&gt;
3319
3320
3321
3322&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3323
3324&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3325Matthias Rauterberg, Lars Oestreicher, John Grundy
3326&lt;/p&gt;&lt;/div&gt;
3327
3328
3329
3330&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3331
3332&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3333This is the proceedings for the INTERACT97 combined workshop on &amp;ldquo;CSCW in HCI-worldwide&amp;rdquo;. The position papers in this proceedings are those selected from topics relating to HCI community development worldwide and to CSCW issues. Originally these were to be two separate INTERACT workshops, but were combined to ensure sufficient participation for a combined workshop to run.
3334&lt;/p&gt;&lt;/div&gt;
3335
3336
3337
3338&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3339
3340&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3341
3342&lt;/p&gt;&lt;/div&gt;
3343
3344
3345
3346&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3347
3348&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3349The combined workshop has been split into two separate sessions to run in the morning of July 15&lt;sup&gt;th&lt;/sup&gt;, Sydney, Australia. One to discuss the issues relating to the position papers focusing on general CSCW systems, the other to the development of HCI communities in a worldwide context. The CSCW session uses as a case study a proposed groupware tool for facilitating the development of an HCI database with a worldwide geographical distribution. The HCI community session focuses on developing the content for such a database, in order for it to foster the continued development of HCI communities. The afternoon session of the combined workshop involves a joint discussion of the case study groupware tool, in terms of its content and likely groupware facilities.
3350&lt;/p&gt;&lt;/div&gt;
3351
3352
3353
3354&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3355
3356&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3357
3358&lt;/p&gt;&lt;/div&gt;
3359
3360
3361
3362&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3363
3364&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3365The position papers have been grouped into those focusing on HCI communities and hence content issues for a groupware database, and those focusing on CSCW and groupware issues, and hence likely groupware support in the proposed HCI database/collaboration tools. We hope that you find the position papers in this proceedings offer a wide range of interesting reports of HCI community development worldwide, leading CSCW system research, and that a groupware tool supporting aspects of a worldwide HCI database can draw upon the varied work reported.
3366&lt;/p&gt;&lt;/div&gt;
3367
3368
3369
3370&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3371
3372&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3373
3374&lt;/p&gt;&lt;/div&gt;
3375
3376
3377
3378&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3379
3380&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3381
3382&lt;/p&gt;&lt;/div&gt;
3383
3384
3385
3386&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3387
3388&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3389
3390&lt;/p&gt;&lt;/div&gt;
3391
3392
3393
3394&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3395
3396&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
339797/17
3398&lt;/p&gt;&lt;/div&gt;
3399
3400
3401
3402&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3403
3404&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3405Internationalising a spreadsheet for Pacific Basin languages
3406&lt;/p&gt;&lt;/div&gt;
3407
3408
3409
3410&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3411
3412&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3413Robert Barbour, Alvin Yeo
3414&lt;/p&gt;&lt;/div&gt;
3415
3416
3417
3418&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3419
3420&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3421As people trade and engage in commerce, an economically dominant culture tends to migrate language into other recently contacted cultures. Information technology (IT) can accelerate enculturation and promote the expansion of western hegemony in IT. Equally, IT can present a culturally appropriate interface to the user that promotes the preservation of culture and language with very little additional effort. In this paper a spreadsheet is internationalised to accept languages from the Latin-1 character set such as English, Maori and Bahasa Melayu (Malaysia's national language). A technique that allows a non-programmer to add a new language to the spreadsheet is described. The technique could also be used to internationalise other software at the point of design by following the steps we outline.
3422&lt;/p&gt;&lt;/div&gt;
3423
3424
3425
3426&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3427
3428&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3429
3430&lt;/p&gt;&lt;/div&gt;
3431
3432
3433
3434&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3435
3436&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3437
3438&lt;/p&gt;&lt;/div&gt;
3439
3440
3441
3442&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3443
3444&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3445
3446&lt;/p&gt;&lt;/div&gt;
3447
3448
3449
3450&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3451
3452&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
345397/18
3454&lt;/p&gt;&lt;/div&gt;
3455
3456
3457
3458&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3459
3460&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3461Localising a spreadsheet: an Iban example
3462&lt;/p&gt;&lt;/div&gt;
3463
3464
3465
3466&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3467
3468&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3469Alvin Yeo, Robert Barbour
3470&lt;/p&gt;&lt;/div&gt;
3471
3472
3473
3474&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3475
3476&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3477Presently, there is little localisation of software to smaller cultures if it is not economically viable. We believe software should also be localised to the languages of small cultures in order to sustain and preserve these small cultures. As an example, we localised a spreadsheet from English to Iban. The process in which we carried out the localisation can be used as a framework for the localisation of software to languages of small ethnic minorities. Some problems faced during the localisation process are also discussed.
3478&lt;/p&gt;&lt;/div&gt;
3479
3480
3481
3482&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3483
3484&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3485
3486&lt;/p&gt;&lt;/div&gt;
3487
3488
3489
3490&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3491
3492&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3493
3494&lt;/p&gt;&lt;/div&gt;
3495
3496
3497
3498&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3499
3500&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3501
3502&lt;/p&gt;&lt;/div&gt;
3503
3504
3505
3506&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3507
3508&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
350997/19
3510&lt;/p&gt;&lt;/div&gt;
3511
3512
3513
3514&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3515
3516&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3517Strategies of internationalisation and localisation: a postmodernist/s perspective
3518&lt;/p&gt;&lt;/div&gt;
3519
3520
3521
3522&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3523
3524&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3525Alvin Yeo, Robert Barbour
3526&lt;/p&gt;&lt;/div&gt;
3527
3528
3529
3530&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3531
3532&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3533Many software companies today are developing software not only for local consumption but for the rest of the world. We introduce the concepts of internationalisation and localisation and discuss some techniques using these processes. An examination of postmodern critique with respect to the software industry is also reported. In addition, we also feature our proposed internationalisation technique that was inspired by taking into account the researches of postmodern philosophers and mathematicians. As illustrated in our prototype, the technique empowers non-programmers to localise their own software. Further development of the technique and its implications on user interfaces and the future of software internationalisation and localisation are discussed.
3534&lt;/p&gt;&lt;/div&gt;
3535
3536
3537
3538&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3539
3540&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3541
3542&lt;/p&gt;&lt;/div&gt;
3543
3544
3545
3546&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3547
3548&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3549
3550&lt;/p&gt;&lt;/div&gt;
3551
3552
3553
3554&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3555
3556&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
355797/20
3558&lt;/p&gt;&lt;/div&gt;
3559
3560
3561
3562&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3563
3564&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3565Language use in software
3566&lt;/p&gt;&lt;/div&gt;
3567
3568
3569
3570&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3571
3572&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3573Alvin Yeo, Robert Barbour
3574&lt;/p&gt;&lt;/div&gt;
3575
3576
3577
3578&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3579
3580&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3581Many of the popular software we use today are in English. Very few software applications are available in minority languages. Besides economic goals, we justify why software should be made available to smaller cultures. Furthermore, there is evidence that people learn and progress faster in software in their mother tongue (Griffiths et at, 1994) (Krock, 1996). We hypothesise that experienced users of English spreadsheet can easily migrate to a spreadsheet in their native tongue i.e. Bahasa Melayu (Malaysia's national language). Observations made in the study suggest that the native speakers of Bahasa Melayu had difficulties with the Bahasa Melayu interface. The subjects' main difficulty was their unfamiliarity with computing terminology in Bahasa Melayu. We present possible strategies to increase the use of Bahasa Melayu in IT. These strategies may also be used to promote the use of other minority languages in IT.
3582&lt;/p&gt;&lt;/div&gt;
3583
3584
3585
3586&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3587
3588&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3589
3590&lt;/p&gt;&lt;/div&gt;
3591
3592
3593
3594&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3595
3596&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3597
3598&lt;/p&gt;&lt;/div&gt;
3599
3600
3601
3602&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3603
3604&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3605
3606&lt;/p&gt;&lt;/div&gt;
3607
3608
3609
3610&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3611
3612&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
361397/21
3614&lt;/p&gt;&lt;/div&gt;
3615
3616
3617
3618&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3619
3620&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3621Usability testing: a Malaysian study
3622&lt;/p&gt;&lt;/div&gt;
3623
3624
3625
3626&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3627
3628&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3629Alvin Yeo, Robert Barbour, Mark Apperley
3630&lt;/p&gt;&lt;/div&gt;
3631
3632
3633
3634&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3635
3636&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3637An exploratory study of software assessment techniques is conducted in Malaysia. Subjects in the study comprised staff members of a Malaysian university with a high Information Technology (IT) presence. The subjects assessed a spreadsheet tool with a Bahasa Melayu (Malaysia's national language) interface. Software evaluation techniques used include the think aloud method, interviews and the System Usability Scale. The responses in the various techniques used are reported and initial results indicate idiosyncratic behaviour of Malaysian subjects. The implications of the findings are also discussed.
3638&lt;/p&gt;&lt;/div&gt;
3639
3640
3641
3642&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3643
3644&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3645
3646&lt;/p&gt;&lt;/div&gt;
3647
3648
3649
3650&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3651
3652&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3653
3654&lt;/p&gt;&lt;/div&gt;
3655
3656
3657
3658&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3659
3660&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3661
3662&lt;/p&gt;&lt;/div&gt;
3663
3664
3665
3666&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3667
3668&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
366997/22
3670&lt;/p&gt;&lt;/div&gt;
3671
3672
3673
3674&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3675
3676&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3677Inducing cost-sensitive trees via instance-weighting
3678&lt;/p&gt;&lt;/div&gt;
3679
3680
3681
3682&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3683
3684&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3685Kai Ming Ting
3686&lt;/p&gt;&lt;/div&gt;
3687
3688
3689
3690&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3691
3692&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3693We introduce an instance-weighting method to induce cost-sensitive trees in this paper. It is a generalization of the standard tree induction process where only the initial instance weights determine the type of tree (i.e., minimum error trees or minimum cost trees) to be induced. We demonstrate that it can be easily adopted to an existing tree learning algorithm.
3694&lt;/p&gt;&lt;/div&gt;
3695
3696
3697
3698&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3699
3700&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3701
3702&lt;/p&gt;&lt;/div&gt;
3703
3704
3705
3706&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3707
3708&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3709Previous research gave insufficient evidence to support the fact that the greedy divide-and-conquer algorithm can effectively induce a truly cost-sensitive tree directly from the training data. We provide this empirical evidence in this paper. The algorithm employing the instance-weighting method is found to be comparable to or better than both C4.5 and C5 in terms of total misclassification costs, tree size and the number of high cost errors. The instance-weighting method is also simpler and more effective in implementation than a method based on altered priors.
3710&lt;/p&gt;&lt;/div&gt;
3711
3712
3713
3714&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3715
3716&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3717
3718&lt;/p&gt;&lt;/div&gt;
3719
3720
3721
3722&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3723
3724&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3725
3726&lt;/p&gt;&lt;/div&gt;
3727
3728
3729
3730&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3731
3732&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
373397/23
3734&lt;/p&gt;&lt;/div&gt;
3735
3736
3737
3738&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3739
3740&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3741Fast convergence with a greedy tag-phrase dictionary
3742&lt;/p&gt;&lt;/div&gt;
3743
3744
3745
3746&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3747
3748&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3749Ross Peeters, Tony C. Smith
3750&lt;/p&gt;&lt;/div&gt;
3751
3752
3753
3754&lt;p&gt;&lt;div name=&quot;Body Text&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3755
3756&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3757The best general-purpose compression schemes make their gains by estimating a probability distribution over all possible next symbols given the context established by some number of previous symbols. Such context models typically obtain good compression results for plain text by taking advantage of regularities in character sequences. Frequent words and syllables can be incorporated into the model quickly and thereafter used for reasonably accurate prediction. However, the precise context in which frequent patterns emerge is often extremely varied, and each new word or phrase immediately introduces new contexts which can adversely affect the compression rate
3758&lt;/p&gt;&lt;/div&gt;
3759
3760
3761
3762&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3763
3764&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3765
3766&lt;/p&gt;&lt;/div&gt;
3767
3768
3769
3770&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3771
3772&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3773A great deal of the structural regularity in a natural language is given rather more by properties of its grammar than by the orthographic transcription of its phonology. This implies that access to a grammatical abstraction might lead to good compression. While grammatical models have been used successfully for compressing computer programs [4], grammar-based compression of plain text has received little attention, primarily because of the difficulties associated with constructing a suitable natural language grammar. But even without a precise formulation of the syntax of a language, there is a linguistic abstraction which is easily accessed and which demonstrates a high degree of regularity which can be exploited for compression purposes-namely, lexical categories.
3774&lt;/p&gt;&lt;/div&gt;
3775
3776
3777
3778&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3779
3780&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3781
3782&lt;/p&gt;&lt;/div&gt;
3783
3784
3785
3786&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3787
3788&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3789
3790&lt;/p&gt;&lt;/div&gt;
3791
3792
3793
3794&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3795
3796&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
379797/24
3798&lt;/p&gt;&lt;/div&gt;
3799
3800
3801
3802&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3803
3804&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3805Tag based models of English text
3806&lt;/p&gt;&lt;/div&gt;
3807
3808
3809
3810&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3811
3812&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3813W. J. Teahan, John G. Cleary
3814&lt;/p&gt;&lt;/div&gt;
3815
3816
3817
3818&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3819
3820&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3821The problem of compressing English text is important both because of the ubiquity of English as a target for compression and because of the light that compression can shed on the structure of English. English text is examined in conjunction with additional information about the parts of speech of each word in the text (these are referred to as &amp;ldquo;tags&amp;rdquo;). It is shown that the tags plus the text can be compressed more than the text alone. Essentially the tags can be compressed for nothing or even a small net saving in size. A comparison is made of a number of different ways of integrating compression of tags and text using an escape mechanism similar to PPM. These are also compared with standard word based and character based compression programs. The result is that the tag character and word based schemes always outperform the character based schemes. Overall, the tag based schemes outperform the word based schemes. We conclude by conjecturing that tags chosen for compression rather than linguistic purposes would perform even better.
3822&lt;/p&gt;&lt;/div&gt;
3823
3824
3825
3826&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3827
3828&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3829
3830&lt;/p&gt;&lt;/div&gt;
3831
3832
3833
3834&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3835
3836&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3837
3838&lt;/p&gt;&lt;/div&gt;
3839
3840
3841
3842&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3843
3844&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
384597/25
3846&lt;/p&gt;&lt;/div&gt;
3847
3848
3849
3850&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3851
3852&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3853Musical image compression
3854&lt;/p&gt;&lt;/div&gt;
3855
3856
3857
3858&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3859
3860&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3861David Bainbridge, Stuart Inglis
3862&lt;/p&gt;&lt;/div&gt;
3863
3864
3865
3866&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3867
3868&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3869Optical music recognition aims to convert the vast repositories of sheet music in the world into an on-line digital format [Bai97]. In the near future it will be possible to assimilate music into digital libraries and users will be able to perform searches based on a sung melody in addition to typical text-based searching [MSW+96]. An important requirement for such a system is the ability to reproduce the original score as accurately as possible. Due to the huge amount of sheet music available, the efficient storage of musical images is an important topic of study.
3870&lt;/p&gt;&lt;/div&gt;
3871
3872
3873
3874&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3875
3876&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3877
3878&lt;/p&gt;&lt;/div&gt;
3879
3880
3881
3882&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3883
3884&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3885This paper investigates whether the &amp;ldquo;knowledge&amp;rdquo; extracted from the optical music recognition (OMR) process can be exploited to gain higher compression than the JBIG international standard for bi-level image compression. We present a hybrid approach where the primitive shapes of music extracted by the optical music recognition process-note heads, note stems, staff lines and so forth-are fed into a graphical symbol based compression scheme originally designed for images containing mainly printed text. Using this hybrid approach the average compression rate for a single page is improved by 3.5% over JBIG. When multiple pages with similar typography are processed in sequence, the file size is decreased by 4-8%.
3886&lt;/p&gt;&lt;/div&gt;
3887
3888
3889
3890&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3891
3892&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3893
3894&lt;/p&gt;&lt;/div&gt;
3895
3896
3897
3898&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3899
3900&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3901Section 2 presents the relevant background to both optical music recognition and textual image compression. Section 3 describes the experiments performed on 66 test images, outlining the combinations of parameters that were examined to give the best results. The initial results and refinements are presented in Section 4, and we conclude in the last section by summarizing the findings of this work.
3902&lt;/p&gt;&lt;/div&gt;
3903
3904
3905
3906&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3907
3908&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3909
3910&lt;/p&gt;&lt;/div&gt;
3911
3912
3913
3914&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3915
3916&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3917
3918&lt;/p&gt;&lt;/div&gt;
3919
3920
3921
3922&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3923
3924&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3925
3926&lt;/p&gt;&lt;/div&gt;
3927
3928
3929
3930&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3931
3932&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
393397/26
3934&lt;/p&gt;&lt;/div&gt;
3935
3936
3937
3938&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3939
3940&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3941Correcting English text using PPM models
3942&lt;/p&gt;&lt;/div&gt;
3943
3944
3945
3946&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3947
3948&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3949W. J. Teahan, S. Inglis, J. G. Cleary, G. Holmes
3950&lt;/p&gt;&lt;/div&gt;
3951
3952
3953
3954&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3955
3956&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3957An essential component of many applications in natural language processing is a language modeler able to correct errors in the text being processed. For optical character recognition (OCR), poor scanning quality or extraneous pixels in the image may cause one or more characters to be mis-recognized; while for spelling correction, two characters may be transposed, or a character may be inadvertently inserted or missed out.
3958&lt;/p&gt;&lt;/div&gt;
3959
3960
3961
3962&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3963
3964&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3965
3966&lt;/p&gt;&lt;/div&gt;
3967
3968
3969
3970&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3971
3972&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3973This paper describes a method for correcting English text using a PPM model. A method that segments words in English text is introduced and is shown to be a significant improvement over previously used methods. A similar technique is also applied as a post-processing stage after pages have been recognized by a state-of-the-art commercial OCR system. We show that the accuracy of the OCR system can be increased from 95.9% to 96.6%, a decrease of about 10 errors per page.
3974&lt;/p&gt;&lt;/div&gt;
3975
3976
3977
3978&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3979
3980&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3981
3982&lt;/p&gt;&lt;/div&gt;
3983
3984
3985
3986&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3987
3988&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3989
3990&lt;/p&gt;&lt;/div&gt;
3991
3992
3993
3994&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
3995
3996&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
3997
3998&lt;/p&gt;&lt;/div&gt;
3999
4000
4001
4002&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
4003
4004&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
4005
4006&lt;/p&gt;&lt;/div&gt;
4007
4008
4009
4010&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
4011
4012&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
401397/27
4014&lt;/p&gt;&lt;/div&gt;
4015
4016
4017
4018&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
4019
4020&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
4021Constraints on parallelism beyond 10 instructions per cycle
4022&lt;/p&gt;&lt;/div&gt;
4023
4024
4025
4026&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
4027
4028&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
4029John G. Cleary, Richard H. Littin, J. A. David McWha, Murray W. Pearson
4030&lt;/p&gt;&lt;/div&gt;
4031
4032
4033
4034&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
4035
4036&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
4037The problem of extracting Instruction Level Parallelism at levels of 10 instructions per clock and higher is considered. Two different architectures which use speculation on memory accesses to achieve this level of performance are reviewed. It is pointed out that while this form of speculation gives high potential parallelism it is necessary to retain execution state so that incorrect speculation can be detected and subsequently squashed. Simulation results show that the space to store such state is a critical resource in obtaining good speedup. To make good use of the space it is essential that state be stored efficiently and that it be retired as soon as possible. A number of techniques for extracting the best usage from the available state storage are introduced.
4038&lt;/p&gt;&lt;/div&gt;
4039
4040
4041
4042&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
4043
4044&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
4045
4046&lt;/p&gt;&lt;/div&gt;
4047
4048
4049
4050&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
4051
4052&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
4053
4054&lt;/p&gt;&lt;/div&gt;
4055
4056
4057
4058&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
4059
4060&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
4061
4062&lt;/p&gt;&lt;/div&gt;
4063
4064
4065
4066&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
4067
4068&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
406997/28
4070&lt;/p&gt;&lt;/div&gt;
4071
4072
4073
4074&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
4075
4076&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
4077Effects of re-ordered memory operations on parallelism
4078&lt;/p&gt;&lt;/div&gt;
4079
4080
4081
4082&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
4083
4084&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
4085Richard H. Littin, John G. Cleary
4086&lt;/p&gt;&lt;/div&gt;
4087
4088
4089
4090&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
4091
4092&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
4093The performance effect of permitting different memory operations to be re-ordered is examined. The available parallelism is computed using a machine code simulator. A range of possible restrictions on the re-ordering of memory operations is considered: from the purely sequential case where no re-ordering is permitted; to the completely permissive one where memory operations may occur in any order so that the parallelism is restricted only by data dependencies. A general conclusion is drawn that to reliably obtain parallelism beyond 10 instructions per clock will require an ability to re-order all memory instructions. A brief description of a feasible architecture capable of this is given.
4094&lt;/p&gt;&lt;/div&gt;
4095
4096
4097
4098&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
4099
4100&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
4101
4102&lt;/p&gt;&lt;/div&gt;
4103
4104
4105
4106&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
4107
4108&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
4109
4110&lt;/p&gt;&lt;/div&gt;
4111
4112
4113
4114&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
4115
4116&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
4117
4118&lt;/p&gt;&lt;/div&gt;
4119
4120
4121
4122&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot;margin: 0.00mm -0.14mm 0.00mm 0.00mm; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
4123
4124&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
412597/29
4126&lt;/p&gt;&lt;/div&gt;
4127
4128
4129
4130&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
4131
4132&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
4133OZCHI'96 Industry Session: Sixth Australian Conference on Human-Computer Interaction
4134&lt;/p&gt;&lt;/div&gt;
4135
4136
4137
4138&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
4139
4140&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
4141Edited by Chris Phillips, Janis McKauge
4142&lt;/p&gt;&lt;/div&gt;
4143
4144
4145
4146&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
4147
4148&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
4149The idea for a specific industry session at OZCHI was first mooted at the 1995 conference in Wollongong, during questions following a session of short papers which happened (serendipitously) to be presented by people from industry. An animated discussion took place, most of which was about how OZCHI could be made more relevant to people in industry, be it working as usability consultants, or working within organisations either as usability professionals or as `champions of the cause'. The discussion raised more questions than answers, about the format of such as session, about the challenges of attracting industry participation, and about the best way of publishing the results. Although no real solutions were arrived at, it was enough to place an industry session on the agenda for OZCHI'96.
4150&lt;/p&gt;&lt;/div&gt;
4151
4152
4153
4154&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
4155
4156&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
4157
4158&lt;/p&gt;&lt;/div&gt;
4159
4160
4161
4162&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
4163
4164&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
4165
4166&lt;/p&gt;&lt;/div&gt;
4167
4168
4169
4170&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
4171
4172&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
417397/30
4174&lt;/p&gt;&lt;/div&gt;
4175
4176
4177
4178&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
4179
4180&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
4181Adaptive models of English text
4182&lt;/p&gt;&lt;/div&gt;
4183
4184
4185
4186&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
4187
4188&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
4189W. J. Teahan, John G. Cleary
4190&lt;/p&gt;&lt;/div&gt;
4191
4192
4193
4194&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
4195
4196&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
4197High quality models of English text with performance approaching that of humans is important for many applications including spelling correction, speech recognition, OCR, and encryption. A number of different statistical models of English are compared with each other and with previous estimates from human subjects. It is concluded that the best current models are word based with part of speech tags. Given sufficient training text, they are able to attain performance comparable to humans.
4198&lt;/p&gt;&lt;/div&gt;
4199
4200
4201
4202&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
4203
4204&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
4205
4206&lt;/p&gt;&lt;/div&gt;
4207
4208
4209
4210&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
4211
4212&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
4213
4214&lt;/p&gt;&lt;/div&gt;
4215
4216
4217
4218&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
4219
4220&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
4221
4222&lt;/p&gt;&lt;/div&gt;
4223
4224
4225
4226&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
4227
4228&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
422997/31
4230&lt;/p&gt;&lt;/div&gt;
4231
4232
4233
4234&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
4235
4236&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
4237A graphical user interface for Boolean query specification
4238&lt;/p&gt;&lt;/div&gt;
4239
4240
4241
4242&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
4243
4244&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
4245Steve Jones, Shona McInnes
4246&lt;/p&gt;&lt;/div&gt;
4247
4248
4249
4250&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
4251
4252&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
4253On-line information repositories commonly provide keyword search facilities via textual query languages based on Boolean logic. However, there is evidence to suggest that the syntactical demands of such languages can lead to user errors and adversely affect the time that it takes users to form queries. Users also face difficulties because of the conflict in semantics between AND and OR when used in Boolean logic and English language. We suggest that graphical query languages, in particular Venn-like diagrams, can alleviate the problems that users experience when forming Boolean expressions with textual languages. We describe Vquery, a Venn-diagram based user interface to the New Zealand Digital Library (NZDL). The design of Vquery has been partly motivated by analysis of NZDL usage. We found that few queries contain more than three terms, use of the intersection operator dominates and that query refinement is common. A study of the utility of Venn diagrams for query specification indicates that with little or no training users can interpret and form Venn-like diagrams which accurately correspond to Boolean expressions. The utility of Vquery is considered and directions for future work are proposed.
4254&lt;/p&gt;&lt;/div&gt;
4255
4256
4257
4258&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
4259
4260&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
4261
4262&lt;/p&gt;&lt;/div&gt;
4263
4264
4265
4266&lt;p&gt;&lt;div name=&quot;Normal&quot; align=&quot;left&quot; style=&quot; padding: 0.00mm 0.00mm 0.00mm 0.00mm; &quot;&gt;
4267
4268&lt;p style=&quot;text-indent: 0.00mm; text-align: left; line-height: 4.166667mm; color: Black; background-color: White; &quot;&gt;
4269
4270&lt;/p&gt;&lt;/div&gt;
4271
4272&lt;!--Section Ends--&gt;
4273
4274
4275
4276&lt;!--
4277&lt;hr&gt;
4278&lt;address&gt;
4279&lt;a href=&quot;_httpextlink_&amp;amp;rl=0&amp;amp;href=http:%2f%2fwvware.sourceforge.net&quot;&gt;&lt;img
4280src=&quot;_httpdocimg_/wvSmall.gif&quot; height=31 width=47
4281align=left border=0 alt=&quot;wvWare&quot;&gt;&lt;/a&gt;
4282&lt;a href=&quot;_httpextlink_&amp;amp;rl=0&amp;amp;href=http:%2f%2fvalidator.w3.org%2fcheck%2freferer&quot;&gt;&lt;img
4283src=&quot;_httpdocimg_/vh40.gif&quot; height=31 width=88
4284align=right border=0 alt=&quot;Valid HTML 4.0!&quot;&gt;&lt;/a&gt;
4285Document created with &lt;a href=&quot;_httpextlink_&amp;amp;rl=0&amp;amp;href=http:%2f%2fwvware.sourceforge.net&quot;&gt;wvWare/wvWare version 1.2.4&lt;/a&gt;&lt;br&gt;
4286&lt;/address&gt;
4287--&gt;
4288
4289
4290</Content>
4291</Section>
4292</Archive>
Note: See TracBrowser for help on using the repository browser.