1. Preface to the 2nd edition; 2. Chapter 1. Natural language processing; 3. 1.1 What is NLP?; 4. 1.2 NLP and linguistics; 5. 1.3 Linguistic tools; 6. 1.4 Plan of the book; 7. Chapter 2. Document retrieval; 8. 2.1 Information retrieval; 9. 2.2 Indexing technology; 10. 2.3 Query processing; 11. 2.4 Evaluating search engines; 12. 2.5 Attempts to enhance search performance; 13. 2.6 The future ofWeb searching; 14. Chapter 3. Information extraction; 15. 3.1 The message understanding conferences; 16. 3.2 Regular expressions; 17. 3.3 Finite automata in FASTUS; 18. 3.4 Context-free grammars; 19. 3.5 Limitations of current technology and future research; 20. 3.6 Summary of information extraction; 21. Chapter 4. Text categorization; 22. 4.1 Overview of categorization tasks; 23. 4.2 Handcrafted rule based methods; 24. 4.3 Inductive learning for text classification; 25. 4.4 Nearest neighbor algorithms; 26. 4.5 Combining classifiers; 27. 4.6 Evaluation of text categorization systems; 28. Chapter 5. Text mining; 29. 5.1 What is text mining?; 30. 5.2 Resolving reference and coreference; 31. 5.3 Automatic summarization; 32. 5.4 Testing of automatic summarization programs; 33. 5.5 Prospects for text mining and NLP; 34. References; 35. Index