Always Learning

Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics and Speech Recognition
Daniel Jurafsky, University of Colorado, Boulder
James H. Martin, University of Colorado, Boulder

ISBN-10: 0130950696
ISBN-13:  9780130950697

Publisher:  Prentice Hall
Copyright:  2000
Format:  Paper; 934 pp
Published:  01/26/2000
We're sorry, this product is no longer available and has been replaced with Speech and Language Processing, 2/E.

Please contact your Pearson rep if you are using this product and need instructor resources.


Print this content

In this section:


Description

For undergraduate or advanced undergraduate courses in Classical Natural Language Processing, Statistical Natural Language Processing, Speech Recognition, Computational Linguistics, and Human Language Processing.

This book takes an empirical approach to language processing, based on applying statistical and other machine-learning algorithms to large corporations.

 

Author Website with Resources: http://www.cs.colorado.edu/~martin/slp.html


Features

  • Each chapter is built around one or more worked examples demonstrating the main idea of the chapter.

    • Uses worked examples to illustrate the relative strengths and weaknesses of various approaches. Ex.___

  • Methodology boxes—Included in each chapter.

    • Introduces important methodological tools such as evaluation, wizard of oz techniques, etc. Ex.___

  • Problem sets—Included in each chapter.
  • Integration of speech and text processing—Merges speech processing and natural language processing fields.
  • Empiricist/statistical/machine learning approaches to language processing—Covers all of the new statistical approaches, while still completely covering the earlier more structured and rule-based methods.
  • Includes modern rigorous evaluation metrics.
  • Unified and comprehensive coverage of the field—Covers the fundamental algorithms of various fields, whether originally proposed for spoken or written language.

    • Shows students how the same algorithm can be used for speech recognition and word-sense disambiguation. Ex.___

  • Emphasis on Web and other practical applications.

    • Gives students an understanding of how language-related algorithms can be applied to important real-world problems. Ex.___

  • Emphasis on scientific evaluation—Offers a description of how systems are evaluated with each problem domain.
  • Description of widely available language processing resources.


Table of Contents



 1. Introduction.

I. WORDS.

 2. Regular Expressions and Automata.

 3. Morphology and Finite-State Transducers.

 4. Computational Phonology and Text-to-Speech.

 5. Probabilistic Models of Pronunciation and Spelling.

 6. N-grams.

 7. HMMs and Speech Recognition.

II. SYNTAX.

 8. Word Classes and Part-of-Speech Tagging.

 9. Context-Free Grammars for English.

10. Parsing with Context-Free Grammars.

11. Features and Unification.

12. Lexicalized and Probabilistsic Parsing.

13. Language and Complexity.

III. SEMANTICS.

14. Representing Meaning.

15. Semantic Analysis.

16. Lexical Semantics.

17. Word Sense Disambiguation and Information Retrieval.

IV. PRAGMATICS.

18. Discourse.

19. Dialogue and Conversational Agents.

20. Natural Language Generation.

21. Machine Translation.

APPENDICES.

A. Regular Expression Operators.

B. The Porter Stemming Algorithm.

C. C5 and C7 tagsets.

D. Training HMMs: The Forward-Backward Algorithm.

Bibliography.

Index.



Back to top

close

Sign in to the Instructor Resource Center

Cancel

Print this content

Pearson Higher Education offers special pricing when you choose to package your text with other student resources. If you're interested in creating a cost-saving package for your students contact your Pearson Higher Education representative.

Back to top