1. Editors' Foreword; 2. Part I. Computation for linguistics; 3. Linguistic challenges for computationalists (by Nerbonne, John); 4. Part II. Information extraction & indexing; 5. NLP: An information extraction perspective (by Grishman, Ralph); 6. Semantic indexing using minimum redundancy cut in ontologies (by Seydoux, Florian); 7. Indexing and querying linguistic metadata and document content (by Aswani, Niraj); 8. Term representation with Generalized Latent Semantic Analysis (by Matveeva, Irina); 9. Part III. Parsing; 10. Multilingual dependency parsing: A pipeline approach (by Chang, Ming-Wei); 11. How does treebank annotation influence parsing? Or how not to compare apples and oranges (by Kubler, Sandra); 12. The SenSem project: Syntactico-semantic annotation of sentences in Spanish (by Alonso i Alemany, Laura); 13. Part IV. Anaphora & referring expressions; 14. Generating referring expressions: Past, present and future (by Dale, Robert); 15. A data-driven approach to pronominal anaphora resolution for German (by Hinrichs, Erhard W.); 16. Part V. Classification; 17. Efficient spam analysis for weblogs through URL segmentation (by Nicolov, Nicolas); 18. Document classification using semantic networks with an adaptive similarity measure (by Ginter, Filip); 19. Text summarization for improved text classification (by Mihalcea, Rada); 20. Exploiting linguistic cues to classify rhetorical relations (by Sporleder, Caroline); 21. Part VI. Textual entailment & question answering; 22. Tree edit distance for textual entailment (by Kouylekov, Milen); 23. A genetic algorithm for optimising information retrieval with linguistic features in question answering (by Tiedemann, Jorg); 24. Lexico-syntactic subsumption for textual entailment (by Rus, Vasile); 25. A knowledge-based approach to text-to-text similarity (by Corley, Courtney); 26. Part VII. Ontologies; 27. A simple WWW-based method for semantic word class acquisition (by Shinzato, Keiji); 28. Automatic building of Wordnets (by Barbu, Eduard); 29. Part VIII. Machine translation; 30. Lexical transfer selection using annotated parallel corpora (by Piperidis, Stelios); 31. Multi-perspective evaluation of the FAME speech-to-speech translation system for Catalan, English and Spanish (by Arranz, Victoria); 32. Parallel corpora for medium density languages (by Varga, Daniel); 33. Part IX. Corpora; 34. The role of data in NLP: The case for dataset profiling (by De Roeck, Anne); 35. Even very frequent function words do not distribute homogeneously (by De Roeck, Anne); 36. Exploiting parallel texts to produce a multilingual sense tagged corpus for word sense disambiguation (by Specia, Lucia); 37. Detecting dangerous coordination ambiguities using word distribution (by Chantree, Francis); 38. List and addresses of contributors; 39. Index of subjects and terms