Natural Language Processing Using Very Large Corpora

1. Front Matter

   Pages i-xvii

   PDF

2. Implementation and Evaluation of a German HMM for POS Disambiguation

   • H. Feldweg

   Pages 1-12

3. Improvements in Part-of-Speech Tagging with an Application to German

   • H. Schmid

   Pages 13-25

4. Unsupervised Learning of Disambiguation Rules for Part-of-Speech Tagging

   • E. Brill, M. Pop

   Pages 27-42

5. Tagging French without Lexical Probabilities — Combining Linguistic Knowledge and Statistical Learning

   • E. Tzoukermann, D. Radev, W. Gale

   Pages 43-65

6. Example-Based Sense Tagging of Running Chinese Text

   • X. Tong, C. Huang, C. Guo

   Pages 67-75

7. Disambiguating Noun Groupings with Respect to WordNet Senses

   • P. Resnik

   Pages 77-98

8. A Comparison of Corpus-Based Techniques for Restoring Accents in Spanish and French Text

   • D. Yarowsky

   Pages 99-120

9. Beyond Word N-Grams

   • F. C. Pereira, Y. Singer, N. Tishby

   Pages 121-136

10. Statistical Augmentation of a Chinese Machine-Readable Dictionary

    • P. Fung, D. Wu

    Pages 137-155

11. Text Chunking Using Transformation-Based Learning

    • L. A. Ramshaw, M. P. Marcus

    Pages 157-176

12. Prepositional Phrase Attachment Through a Backed-off Model

    • M. Collins, J. Brooks

    Pages 177-189

13. On the Unsupervised Induction of Phrase-Structure Grammars

    • C. de Marcken

    Pages 191-208

14. Robust Bilingual Word Alignment for Machine Aided Translation

    • I. Dagan, K. Church, W. Gale

    Pages 209-224

15. Iterative Alignment of Syntactic Structures for a Bilingual Corpus

    • R. Grishman

    Pages 225-234

16. Trainable Coarse Bilingual Grammars for Parallel Text Bracketing

    • D. Wu

    Pages 235-252

17. Comparative Discourse Analysis of Parallel Texts

    • P. Van Der Eijk

    Pages 253-268

18. Comparing the Retrieval Performance of English and Japanese Text Databases

    • H. Fujii, W. B. Croft

    Pages 269-282

19. Inverse Document Frequency (IDF): A Measure of Deviations from Poisson

    • K. Church, W. Gale

    Pages 283-295

20. Back Matter

    Pages 297-305

    PDF

ABOUT THIS BOOK This book is intended for researchers who want to keep abreast of cur­ rent developments in corpus-based natural language processing. It is not meant as an introduction to this field; for readers who need one, several entry-level texts are available, including those of (Church and Mercer, 1993; Charniak, 1993; Jelinek, 1997). This book captures the essence of a series of highly successful work­ shops held in the last few years. The response in 1993 to the initial Workshop on Very Large Corpora (Columbus, Ohio) was so enthusias­ tic that we were encouraged to make it an annual event. The following year, we staged the Second Workshop on Very Large Corpora in Ky­ oto. As a way of managing these annual workshops, we then decided to register a special interest group called SIGDAT with the Association for Computational Linguistics. The demand for international forums on corpus-based NLP has been expanding so rapidly that in 1995 SIGDAT was led to organize not only the Third Workshop on Very Large Corpora (Cambridge, Mass. ) but also a complementary workshop entitled From Texts to Tags (Dublin). Obviously, the success of these workshops was in some measure a re­ flection of the growing popularity of corpus-based methods in the NLP community. But first and foremost, it was due to the fact that the work­ shops attracted so many high-quality papers.

• Parsing
• grammar
• knowledge
• language
• learning
• natural language
• natural language processing
• supervised learning

• ISSCO, University of Geneva, Switzerland

  Susan Armstrong, Sandra Manzi

• AT & T Labs-Research, USA

  Kenneth Church

• Xerox Research Centre Europe, France

  Pierre Isabelle

• Bell Laboratories, Lucent, USA

  Evelyne Tzoukermann

• Johns Hopkins University, Baltimore, USA

  David Yarowsky

Policies and ethics