Advances in Natural Language Processing: 7th International Conference on NLP, IceTAL 2010, Reykjavik, Iceland, August 16-18, 2010, Proceedings

Lecture Notes in Artificial Intelligence 6233......Page 1
Advances in Natural Language Processing: 7th International Conference on NLP, IceTAL 2010 / Reykjavik, Iceland, August 16-18, 2010 / Proceedings......Page 2
Preface......Page 4
Organization......Page 5
Table of Contents......Page 8
Reliving the History: The Beginnings of Statistical Machine Translation and Languages with Rich Morphology......Page 12
Harmonizing WordNet and FrameNet......Page 13
Introduction......Page 14
The Original Brill Tagger......Page 15
Adaptation for Inflectional Languages......Page 16
Generalized Transformation Templates......Page 17
Lexical Transformations......Page 18
Parallelization......Page 19
Evaluation......Page 21
Conclusions and Future Work......Page 23
References......Page 24
Embodied Conversational Agents......Page 26
Related Work......Page 27
Conditional Random Fields......Page 28
New Problem Characteristics......Page 29
Implementation......Page 30
Experimental Results......Page 33
Conclusions......Page 35
References......Page 36
Introduction......Page 38
Design of the Scenario......Page 39
Word Space: Latent Semantic Analysis......Page 40
Methods for Distractor Generation......Page 41
Experimental Settings......Page 43
Item Analysis and Distractor Evaluation......Page 45
Interpreting the Results of the Tests......Page 46
References......Page 48
Introduction......Page 50
Related Work......Page 51
Evaluation Datasets......Page 52
Results......Page 53
Conclusions and Future Work......Page 54
References......Page 55
Introduction......Page 56
Linguistic Concepts for a Model of Aspect and Time......Page 57
Linguistic Relations for a Model of Aspect and Time......Page 59
Formal Framework......Page 61
Definitions of Concepts and Relations in the Ontology of Time and Aspect......Page 63
References......Page 66
Introduction......Page 68
Cross-Language Semantic Mapping......Page 69
Multilingual Sentence Dataset......Page 71
Experimental Evaluation of the Proposed Technique......Page 72
Comparative Evaluation of the Proposed Technique......Page 74
Conclusions and Future Work......Page 75
References......Page 76
Introduction......Page 78
Previous Work on Subsentential Paraphrase Acquisition......Page 79
Acquisition of Subsentential Paraphrases from Sentential Paraphrases......Page 80
Term Variant Identification Method (Term)......Page 81
Alignment by Syntactic Fusion Method (Synt)......Page 82
Corpus Collection......Page 84
Experimental Results......Page 86
References......Page 88
Introduction......Page 90
Related Work......Page 91
Summarization Workflow......Page 92
Implementation Details......Page 93
Conclusion and Future Work......Page 94
References......Page 95
Introduction......Page 96
GIR Related Work......Page 97
Random Indexing......Page 99
BoC Document Representation......Page 100
HRR Document Representation......Page 101
Experimental Setup......Page 102
Results......Page 103
References......Page 106
Machine Translation Approach......Page 108
Double Translation Process......Page 109
Other Uses of Machine Translation in RTE Systems......Page 110
Experimental Evaluation and Discussion of the Results......Page 111
References......Page 113
Introduction......Page 114
Using TTR to Represent Frames......Page 115
A TTR Approach to Verbs in Compositional Semantics......Page 116
The Puzzle about Temperature and Prices......Page 118
Fernando's String Theory of Events......Page 119
Word Meaning in Flux......Page 120
Conclusion......Page 123
References......Page 124
Introduction......Page 126
Text Sets and Preprocessing......Page 127
Clustering......Page 128
Experiments and Discussion......Page 129
References......Page 130
Introduction......Page 132
OpenMaTrEx: Training and Translation......Page 133
EBMT-Specific Components......Page 134
A Sample Experiment......Page 135
References......Page 136
Introduction......Page 138
Head Finding Algorithms......Page 140
Bilexical Grammars......Page 141
Induction of Bilexical Grammars......Page 142
Building and Traversing the Search Space......Page 143
Stability of Head Finders......Page 144
Experimental Results......Page 145
Conclusions......Page 147
References......Page 148
Introduction......Page 149
Citation-Based Constraints......Page 151
"Iron-clad" and Heuristic Constraints......Page 152
Greedy Constraints......Page 155
Experimental Results......Page 156
Summary, Conclusions and Future Work......Page 159
References......Page 160
Introduction......Page 161
Principles and Objectives......Page 163
HMM Model......Page 164
CRF Model......Page 165
Evaluation......Page 166
Intrinsic Evaluation of the Segmentation of Texts into Events......Page 167
Evaluation of Text Segmentation for Information Extraction......Page 168
Related Work......Page 169
Conclusion and Future Work......Page 170
References......Page 171
Japanese WordNet......Page 173
Creating the Japanese WordNet......Page 174
Enriching the Adjective Domain in the Japanese WordNet – Detecting Attribute Concepts and Their Values –......Page 175
References......Page 177
Introduction......Page 178
Moses as a Phoneme-to-Phoneme Converter......Page 179
Pivot Paraphrasing Approach......Page 180
Corpus......Page 181
System......Page 183
Evaluation......Page 184
Conclusions......Page 187
References......Page 188
Introduction......Page 190
A Statistical Model......Page 191
Extraction of Text Spans......Page 192
Results......Page 193
References......Page 194
Introduction......Page 196
Situation vs. Perspective......Page 197
Grammatical Diatheses......Page 198
Representation of Grammatical Diatheses......Page 199
Semantic Diatheses......Page 201
Representation of Semantic Diatheses......Page 202
Representation of Locative Semantic Diathesis.......Page 203
Locative Diathesis of Verbs Indicating `Creating Co-occurrence'.......Page 204
Locative Diathesis of Verbs Indicating `Destroying Co-occurrence'.......Page 206
References......Page 207
Introduction......Page 208
Related Work......Page 209
Data......Page 210
Extraction Module......Page 211
Encoding Module......Page 212
Method 2: Extended Lexical Patterns (ELP)......Page 213
Extraction Resource Building......Page 214
Class Inference......Page 215
Combination of Symbolic Methods......Page 216
Results......Page 217
Discussion and Future Work......Page 218
References......Page 219
Introduction......Page 220
Speaker and Listener Actions......Page 221
The Utility Function......Page 222
A Multi-iteration Game Algorithm for Discourse Planning......Page 224
References......Page 225
Introduction......Page 226
Filter-Based Pairwise Classification......Page 227
Morphology with Gertwol......Page 229
Pro3gresDe: The Parser......Page 230
The Price of Real Preprocessing......Page 231
Filtering for Resolution of Bridging Anaphora......Page 232
Related Work......Page 234
References......Page 235
Introduction......Page 237
Analysis of Initial Data......Page 239
Description of the Strategy......Page 241
Analysis and Evaluation of the Strategy......Page 243
Implementation and Usefulness......Page 246
Conclusions......Page 247
References......Page 248
Introduction......Page 249
Collocation......Page 250
Collocation Extraction in Turkish......Page 251
Mutual Information......Page 252
Dunning's Log-Likelihood Test......Page 253
Chi-Square ($X^2$) Test......Page 254
The Base Data Set......Page 255
Results......Page 256
References......Page 259
Introduction......Page 261
Vocabulary Design......Page 262
Vocabulary Evaluation......Page 263
Grammar Design......Page 264
Discussion and Conclusion......Page 265
References......Page 266
Introduction......Page 268
Temporal Expressions Ontology......Page 270
References......Page 273
Introduction......Page 274
Stimuli......Page 275
Results......Page 276
Discussion......Page 278
References......Page 279
Introduction......Page 280
Decision Trees......Page 281
Random Forests......Page 282
Chinese Mandarin STT System......Page 283
Training of RF Models......Page 285
Results......Page 288
References......Page 290
Introduction......Page 292
A Bird's Eye View of Error Detection Techniques......Page 293
Agreement Errors in Basque......Page 294
Syntactic Analysis......Page 295
Saroi: A Tool for Inspecting Dependency Trees......Page 296
Preprocessing......Page 297
Evaluation Methodology......Page 298
Election of the Disambiguation Level......Page 299
Correct corpora.......Page 300
Error corpora.......Page 301
Conclusions and Future Work......Page 302
Introduction......Page 304
Blocks and Scenarios......Page 305
Applications......Page 306
Documents, Bundles and Trees......Page 307
TectoMT Components and Directory Structure......Page 309
Data Formats......Page 310
Other NLP Frameworks......Page 311
Summary......Page 312
Introduction......Page 316
Prototype-Based CLTC Method......Page 317
Baseline Experiments......Page 320
Results from the Proposed Method......Page 321
Conclusions and Future Work......Page 323
Introduction......Page 325
Related Work......Page 326
Proposed Work......Page 327
Experiment and Discussions......Page 328
Conclusion......Page 330
Introduction......Page 331
Two-Stage Corpus-Based Translation Model......Page 333
First Stage in the Proposed Translation Model......Page 334
Second Stage in the Proposed Translation Model......Page 335
Combining Different Translation Models......Page 336
Evaluations on the Retrieval System......Page 337
Evaluations in CLIR......Page 338
References......Page 340
Introduction......Page 343
Collaboratively Constructed Resources (CCR)......Page 344
Wiktionary......Page 345
Endogenous Enrichment......Page 346
Bipartite Graphs Model......Page 347
Random Walk-Based Similarity Computation......Page 348
Evaluation Method......Page 349
Results......Page 350
Suggestion and Validation of Candidates......Page 352
Conclusion and Future Work......Page 353
Introduction......Page 356
The ``Tell Me About...'' Task......Page 357
Related Work......Page 359
Algorithm......Page 360
Evaluation......Page 363
Enhancement of Image Captions......Page 364
Conclusions......Page 365
Introduction......Page 368
Problem Study......Page 369
Information Retrieval and Log Files......Page 370
Related Work......Page 371
Passage Retrieval Based on Query Enrichment......Page 372
Terminological Knowledge......Page 373
How to Find Terms Correlated to Answers......Page 374
Experiments......Page 377
Conclusions......Page 378
Introduction......Page 380
Previous Research......Page 381
A Probabilistic First Order Model......Page 382
The Bigram Models......Page 383
Implementing the Statistical Model Using Weighted Finite-State Transducers......Page 384
The Bigram Models......Page 385
Data......Page 387
Training the Model......Page 388
Discussion and Future Work......Page 389
Conclusions......Page 390
Introduction......Page 392
Question Templates......Page 393
Components of a Text Pattern......Page 394
Flexibility of a Text Pattern......Page 395
Spelling Correction......Page 396
Performance Measurements......Page 398
Precision, Recall, and Correctness......Page 399
Advantages and Limitations......Page 401
References......Page 402
Natural Language......Page 404
Controlled Languages......Page 405
A System to Help When Creating Sentences That Are to Be Pronounced......Page 406
Oral Communication Involving Different Mother Tongues......Page 407
Results and Improvements......Page 409
Conclusion......Page 410
References......Page 411
Introduction......Page 412
Tri-training......Page 413
Data......Page 414
Results......Page 415
Conclusion......Page 416
Introduction......Page 417
Dependency Parsing......Page 418
Stacked Dependency Parsing......Page 419
Generalized Tri-training......Page 420
Algorithm......Page 422
Results......Page 423
Error Analysis and Discussion......Page 424
Conclusion......Page 426
Introduction......Page 429
Apertium......Page 431
Constraint Grammar......Page 432
Rules......Page 433
Evaluation......Page 435
Discussion......Page 437
Conclusion......Page 439
Author Index......Page 441