词义消歧 (西)艾吉瑞(Eneko Agirre) 等 编 著作 下载 pdf 百度网盘 epub 免费 2025 电子版 mobi 在线

本书是"计算语言学与语言科技原文丛书"中的一册。对于计算机来说，要理解人类语言就必须消除歧义，在计算语言学领域，词义消歧（Word Sense Disambiguation，简称WSD）一直是研究者探索的内容。本书是近年来靠前学术界关于词义消歧研究成果的一部集成之作。几乎覆盖了词义消歧研究各个题目，具有重要学术价值。

导读 1

Contributors 16

Foreword 19

Preface 23

1 Introduction 1

Eneko Agirre and Philip Edmonds

1.1 Word Sense Disambiguation 1

1.2 A Brief History of WSD Research 4

1.3 What is a Word Sense？ 8

1.4 Applications of WSD 10

1.5 Basic Approaches to WSD 12

1.6 State-of-the-Art Performance 14

1.7 Promising Directions 15

1.8 Overview of This Book 19

1.9 Further Reading 21

References 22

2 Word Senses 29

Adam Kilgarriff

2.1 Introduction 29

2.2 Lexicographers 30

2.3 Philosophy 32

2.3.1 Meaning is Something You Do 32

2.3.2 The Fregean Tradition and Reification 33

2.3.3 Two Incompatible Semantics？ 33

2.3.4 Implications for Word Senses 34

2.4 Lexicalization 35

2.5 Corpus Evidence 39

2.5.1 Lexicon Size 41

2.5.2 Quotations 42

2.6 Conclusion 43

2.7 Further Reading 44

Acknowledgments 45

References 45

3 Making Sense About Sense 47

Nancy Ide and Yorick Wilks

3.1 Introduction 47

3.2 WSD and the Lexicographers 49

3.3 WSD and Sense Inventories 51

3.4 NLP Applications and WSD 55

3.5 What Level of Sense Distinctions Do We Need for NLP， If Any？ 58

3.6 What Now for WSD？ 64

3.7 Conclusion 68

References 68

4 Evaluation of WSD Systems 75

Martha Palmer， Hwee Tou Ng and Hoa Trang Dang

4.1 Introduction 75

4.1.1 Terminology 76

4.1.2 Overview 80

4.2 Background 81

4.2.1 WordNet and Semcor 81

4.2.2 The Line and Interest Corpora 83

4.2.3 The DSO Corpus 84

4.2.4 Open Mind Word Expert 85

4.3 Evaluation Using Pseudo-Words 86

4.4 Senseval Evaluation Exercises 86

4.4.1 Senseval-187

Evaluation and Scoring 88

4.4.2 Senseval-288

English All-Words Task 89

English Lexical Sample Task 89

4.4.3 Comparison of Tagging Exercises 91

4.5 Sources of Inter-Annotator Disagreement 92

4.6 Granularity of Sense： Groupings for WordNet 95

4.6.1 Criteria for WordNet Sense Grouping 96

4.6.2 Analysis of Sense Grouping 97

4.7 Senseval-398

4.8 Discussion 99

References 102

5 Knowledge-Based Methods for WSD 107

Rada Mihalcea

5.1 Introduction 107

5.2 Lesk Algorithm 108

5.2.1 Variations of the Lesk Algorithm 110

Simulated Annealing 110

Simplified Lesk Algorithm 111

Augmented Semantic Spaces 113

Summary 113

5.3 Semantic Similarity 114

5.3.1 Measures of Semantic Similarity 114

5.3.2 Using Semantic Similarity Within a Local Context 117

5.3.3 Using Semantic Similarity Within a Global Context 118

5.4 Selectional Preferences 119

5.4.1 Preliminaries： Learning Word-to-Word Relations 120

5.4.2 Learning Selectional Preferences 120

5.4.3 Using Selectional Preferences 122

5.5 Heuristics for Word Sense Disambiguation 123

5.5.1 Most Frequent Sense 123

5.5.2 One Sense Per Discourse 124

5.5.3 One Sense Per Collocation 124

5.6 Knowledge-Based Methods at Senseval-2125

5.7 Conclusions 126

References 127

6 Unsupervised Corpus-Based Methods for WSD 133

Ted Pedersen

6.1 Introduction 133

6.1.1 Scope 134

6.1.2 Motivation 136

Distributional Methods 137

Translational Equivalence 139

6.1.3 Approaches 140

6.2 Type-Based Discrimination 141

6.2.1 Representation of Context 142

6.2.2 Algorithms 145

Latent Semantic Analysis （LSA） 146

Hyperspace Analogue to Language （HAL） 147

Clustering By Committee （CBC） 148

6.2.3 Discussion 150

6.3 Token-Based Discrimination 150

6.3.1 Representation of Context 151

6.3.2 Algorithms 151

Context Group Discrimination 152

McQuitty’s Similarity Analysis 154

6.3.3 Discussion 157

6.4 Translational Equivalence 158

6.4.1 Representation of Context 159

6.4.2 Algorithms 159

6.4.3 Discussion 160

6.5 Conclusions and the Way Forward 161

Acknowledgments 162

References 162

7 Supervised Corpus-Based Methods for WSD 167

Lluís M？？rquez， Gerard Escudero， David Martínez and German Rigau

7.1 Introduction to Supervised WSD 167

7.1.1 Machine Learning for Classification 168

An Example on WSD 170

7.2 A Survey of Supervised WSD 171

7.2.1 Main Corpora Used 172

7.2.2 Main Sense Repositories 173

7.2.3 Representation of Examples by Means of Features 174

7.2.4 Main Approaches to Supervised WSD 175

Probabilistic Methods 175

Methods Based on the Similarity of the Examples 176

Methods Based on Discriminating Rules 177

Methods Based on Rule Combination 179

Linear Classifiers and Kernel-Based Approaches 179

Discourse Properties： The Yarowsky Bootstrapping Algorithm 181

7.2.5 Supervised Systems in the Senseval Evaluations 183

7.3 An Empirical Study of Supervised Algorithms for WSD 184

7.3.1 Five Learning Algorithms Under Study 185

Na？ve Bayes （NB） 185

Exemplar-Based Learning （kNN） 186

Decision Lists （DL） 187

AdaBoost （AB） 187

Support Vector Machines （SVM） 189

7.3.2 Empirical Evaluation on the DSO Corpus 190

Experiments 191

7.4 Current Challenges of the Supervised Approach 195

7.4.1 Right-Sized Training Sets 195

7.4.2 Porting Across Corpora 196

7.4.3 The Knowledge Acquisition Bottleneck 197

Automatic Acquisition of Training Examples 198

Active Learning 199

Combining Training Examples from Different Words 199

Parallel Corpora 200

7.4.4 Bootstrapping 201

7.4.5 Feature Selection and Parameter Optimization 202

7.4.6 Combination of Algorithms and Knowledge Sources 203

7.5 Conclusions and Future Trends 205

Acknowledgments 206

References 207

8 Knowledge Sources for WSD 217

Eneko Agirre and Mark Stevenson

8.1 Introduction 217

8.2 Knowledge Sources Relevant to WSD 218

8.2.1 Syntactic 219

Part of Speech （KS 1） 219

Morphology （KS 2） 219

Collocations （KS 3） 220

Subcategorization （KS 4） 220

8.2.2 Semantic 220

Frequency of Senses （KS 5） 220

Semantic Word Associations （KS 6） 221

Selectional Preferences （KS 7） 221

Semantic Roles （KS 8） 222

8.2.3 Pragmatic／Topical 222

Domain （KS 9） 222

Topical Word Association （KS 10） 222

Pragmatics （KS 11） 223

8.3 Features and Lexical Resources 223

8.3.1 Target-Word Specific Features 224

8.3.2 Local Features 225

8.3.3 Global Features 227

8.4 Identifying Knowledge Sources in Actual Systems 228

8.4.1 Senseval-2 Systems 229

8.4.2 Senseval-3 Systems 231

8.5 Comparison of Experimental Results 231

8.5.1 Senseval Results 232

8.5.2 Yarowsky and Florian （2002） 233

8.5.3 Lee and Ng （2002） 234

8.5.4 Martínez et al.（2002） 237

8.5.5 Agirre and Martínez （2001 a） 238

8.5.6 Stevenson and Wilks （2001） 240

8.6 Discussion 242

8.7 Conclusions 245

Acknowledgments 246

References 247

9 Automatic Acquisition of Lexical Information and Examples 253

Julio Gonzalo and Felisa Verdejo

9.1 Introduction 253

9.2 Mining Topical Knowledge About Word Senses 254

9.2.1 Topic Signatures 255

9.2.2 Association of Web Directories to Word Senses 257

9.3 Automatic Acquisition of Sense-Tagged Corpora 258

9.3.1 Acquisition by Direct Web Searching 258

9.3.2 Bootstrapping from Seed Examples 261

9.3.3 Acquisition via Web Directories 263

9.3.4 Acquisition via Cross-Language Evidence 264

9.3.5 Web-Based Cooperative Annotation 268

9.4 Discussion 269

Acknowledgments 271

References 272

10 Domain-Specific WSD 275

Paul Buitelaar， Bernardo Magnini， Carlo Strapparava and Piek Vossen

10.1 Introduction 275

10.2 Approaches to Domain-Specific WSD 277

10.2.1 Subject Codes 277

10.2.2 Topic Signatures and Topic Variation 282

Topic Signatures 282

Topic Variation 283

10.2.3 Domain Tuning 284

Top-down Domain Tuning 285

Bottom-up Domain Tuning 285

10.3 Domain-Specific Disambiguation in Applications 288

10.3.1 User-Modeling for Recommender Systems 288

10.3.2 Cross-Lingual Information Retrieval 289

10.3.3 The MEANING Project 292

10.4 Conclusions 295

References 296

11 WSD in NLP Applications 299

Philip Resnik

11.1 Introduction 299

11.2 Why WSD？ 300

Argument from Faith 300

Argument by Analogy 301

Argument from Specific Applications 302

11.3 Traditional WSD in Applications 303

11.3.1 WSD in Traditional Information Retrieval 304

11.3.2 WSD in Applications Related to Information Retrieval 307

Cross-Language IR 308

Question Answering 309

Document Classification 312

11.3.3 WSD in Traditional Machine Translation 313

11.3.4 Sense Ambiguity in Statistical Machine Translation 315

11.3.5 Other Emerging Applications 317

11.4 Alternative Conceptions of Word Sense 320

11.4.1 Richer Linguistic Representations 320

11.4.2 Patterns of Usage 321

11.4.3 Cross-Language Relationships 323

11.5 Conclusions 325

Acknowledgments 325

References 326

A Resources for WSD 339

A.1 Sense Inventories 339

A.1.1 Dictionaries 339

A.1.2 Thesauri 341

A.1.3 Lexical Knowledge Bases 341

A.2 Corpora 343

A.2.1 Raw Corpora 343

A.2.2 Sense-Tagged Corpora 345

A.2.3 Automatically Tagged Corpora 347

A.3 Other Resources 348

A.3.1 Software 348

A.3.2 Utilities， Demos， and Data 349

A.3.3 Language Data Providers 350

A.3.4 Organizations and Mailing Lists 350

Index of Terms 353

Index of Authors and Algorithms 361

艾吉瑞，西班牙国立巴斯克大学副教授。

暂无出版社相关信息，正在全力查找中！

    On the other hand, it is certainly possible that sufficiently separate senses can be identified using multi-lingual criteria-i.e., by identifying senses of the same homograph that have different translations in some sig-nificant number of other languages-as discussed in Section 3.3.For example, the two senses of paper cited above are translated in French as journal and papier, respectivcly; similarly, the two etymologically-related senses of nail (fingernail and the metal object that one hammers) are,trans-lated as ongle and ctou.At the same time, there is a danger in relying on cross-lingualism as the basis of sense, since the same historical processes of sense "chaining" (Cruse 1986, Lakoff 1987) can occur in different an guages.For example, the English wing and its equivalent ala in ltalian have extended their original sense in the same way, from birds to air planes, to buildings, and even to soccer positions.The Italian-Englisn cross-corpus correlations of the two words would lead to the conclusion that both have a single sense, when in fact they have wide sense deviations approaching the homographic.

Another source of information concerning relevant sense distinctions is domain, as discussed in Chapter 10.If senses of a given word are distin- guished by their use in particular domains, this could offer evidence that they are distinguishable at the homograph-like level.At the same time, senses that are not distinguished by domain-take, for example, the sense of bank as a finan institution versus its sense as a building that houses a fman institution-might, for all practical purposes, be regarded as a single, homograph-level sense.

在线阅读地址：词义消歧 (西)艾吉瑞(Eneko Agirre) 等 编 著作在线阅读

在线听书地址：词义消歧 (西)艾吉瑞(Eneko Agirre) 等 编 著作在线收听

在线购买地址：词义消歧 (西)艾吉瑞(Eneko Agirre) 等 编 著作在线购买

暂无原文赏析，正在全力查找中！

编辑推荐

《词义消歧——算法与应用(英文影印版）》是本全面探讨词义消歧的书，对于重要的算法、方式、指标、结果、哲学问题和应用，都有涉略，并有这个领域的非常不错学者对本领域的历史及发展所做的较为全面的综述。研究者可以从本书了解到本领域的成果和发展趋势，开发人员可以从本书了解一些技术和方法。