1. Editors' Foreword; 2. I. Invited lectures; 3. A type-theoretic approach to anaphora and ellipsis resolution (by Fox, Chris); 4. Human dialogue modelling using machine learning (by Wilks, Yorick); 5. Learning domain theories (by Pulman, Stephen G.); 6. Recent developments in temporal information extraction (by Mani, Inderjeet); 7. Annotation-based finite state processing in a large-scale NLP arhitecture (by Boguraev, Branimir K.); 8. II. Lexical semantics and lexical knowledge acquisition; 9. Acquiring lexical paraphrases from a single corpus (by Glickman, Oren); 10. Multi-word collocation extraction by syntactic composition of collocation bigrams (by Seretan, Violeta); 11. Combining independent modules in lexical multiple-choice problems (by Turney, Peter D.); 12. Roget's thesaurus and semantic similarity (by Jarmasz, Mario); 13. Clustering WordNet word senses (by Agirre, Eneko); 14. Inducing hyperlinking rules in text collections (by Basili, Roberto); 15. Near-synonym choice in natural language generation (by Inkpen, Diana Zaiu); 16. III. Tagging, parsing and syntax; 17. Fast and accurate part-of-speech tagging: The SVM approach revisited (by Gimenez, Jesus); 18. Part-of-speech tagging with minimal lexicalization (by Savova, Virginia); 19. Accurate annotation: An efficiency metric (by Branco, Antonio); 20. Structured parameter estimation for LFG-DOP (by Hearne, Mary); 21. Parsing without grammar - Using complete trees instead (by Kubler, Sandra); 22. Phrase recognition by filtering and ranking with perceptrons (by Carreras, Xavier); 23. Cascaded finite-state partial parsing: A larger-first approach (by Delden, Sebastian van); 24. A constraint-based bottom-up counterpart to definite clause grammars (by Christiansen, Henning); 25. IV. Information extraction; 26. Using parallel texts to improve recall in botany (by McGee Wood, Mary); 27. Marking atomic events in sets of related texts (by Filatova, Elena); 28. Semantically driven approach for scenario recognition in the IE system FRET (by Boytcheva, Svetla); 29. A framework for named entity recognition in the open domain (by Evans, Richard J.); 30. V. TEXT SUMMARISATION AND DOCUMENT PROCESSING; 31. Latent semantic analysis and the construction of coherent extracts (by Miller, Tristan); 32. Facilitating email thread access by extractive summary generation (by Nenkova, Ani); 33. Towards deeper understanding of the latent semantic analysis performance (by Nakov, Preslav); 34. Automatic linking of similar texts across languages (by Pouliquen, Bruno); 35. VI. OTHER NLP TOPICS; 36. Verb phrase ellipsis detection using machine learning techniques (by Nielsen, Leif Arda); 37. HPSG-based annotation scheme for corpora development and parsing evaluation (by Simov, Kiril Iv.); 38. Arabic Morpho-syntax for Text-to-Speech (by Ramsay, Allan); 39. Guessing morphological classes of unknown German nouns (by Nakov, Preslav); 40. Building sense tagged corpora with volunteer contributions over the Web (by Mihalcea, Rada); 41. Reducing false positives by expert combination in automatic keyword indexing (by Hulth, Anette); 42. Socrates: A question answering prototype for Bulgarian (by Tanev, Hristo T.); 43. Unsupervised natural language disambiguation using non-ambiguous words (by Mihalcea, Rada); 44. List of Contributors; 45. Index