Chapters in this book

1. Prelim pages i
2. Table of contents v
3. Editors’ Foreword ix
4. I. Invited lectures
5. A type-theoretic approach to anaphora and ellipsis resolution 1
6. Human dialogue modelling using machine learning 17
7. Learning domain theories 29
8. Recent developments in temporal information extraction 45
9. Annotation-based finite state processing in a large-scale NLP arhitecture 61
10. II. Lexical semantics and lexical knowledge acquisition
11. Acquiring lexical paraphrases from a single corpus 81
12. Multi-word collocation extraction by syntactic composition of collocation bigrams 91
13. Combining independent modules in lexical multiple-choice problems 101
14. Roget’s thesaurus and semantic similarity 111
15. Clustering WordNet word senses 121
16. Inducing hyperlinking rules in text collections 131
17. Near-synonym choice in natural language generation 141
18. III. Tagging, parsing and syntax
19. Fast and accurate part-of-speech tagging 153
20. Part-of-speech tagging with minimal lexicalization 163
21. Accurate annotation 173
22. Structured parameter estimation for LFG-DOP 183
23. Parsing without grammar — Using complete trees instead 193
24. Phrase recognition by filtering and ranking with perceptrons 205
25. Cascaded finite-state partial parsing 217
26. A constraint-based bottom-up counterpart to definite clause grammars 227
27. IV. Information extraction
28. Using parallel texts to improve recall in botany 237
29. Marking atomic events in sets of related texts 247
30. Semantically driven approach for scenario recognition in the IE system FRET 257
31. A framework for named entity recognition in the open domain 267
32. V. TEXT SUMMARISATION AND DOCUMENT PROCESSING
33. Latent semantic analysis and the construction of coherent extracts 277
34. Facilitating email thread access by extractive summary generation 287
35. Towards deeper understanding of the latent semantic analysis performance 297
36. Automatic linking of similar texts across languages 307
37. VI. OTHER NLP TOPICS
38. Verb phrase ellipsis detection using machine learning techniques 317
39. HPSG-based annotation scheme for corpora development and parsing evaluation 327
40. Arabic Morpho-syntax for Text-to-Speech 337
41. Guessing morphological classes of unknown German nouns 347
42. Building sense tagged corpora with volunteer contributions over the Web 357
43. Reducing false positives by expert combination in automatic keyword indexing 367
44. Socrates 377
45. Unsupervised natural language disambiguation using non-ambiguous words 387
46. List of Contributors 397
47. Index 399