Product Description

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

An explosion of Web-based language techniques, merging of distinct fields, availability of phone-based dialogue systems, and much more make this an exciting time in speech and language processing. The first of its kind to thoroughly cover language technology — at all levels and with all modern technologies — this text takes an empirical approach to the subject, based on applying statistical and other machine-learning algorithms to large corporations. The authors cover areas that traditionally are taught in different courses, to describe a unified vision of speech and language processing. Emphasis is on practical applications and scientific evaluation. An accompanying Website contains teaching materials for instructors, with pointers to language processing resources on the Web. The Second Edition offers a significant amount of new and extended material.

Supplements:

Click on the "Resources" tab to View Downloadable Files:

• Solutions (available 8/15/08)
• Power Point Lecture Slides (available 8/15/08)

For additional resources visit the author website:

http://www.cs.colorado.edu/~martin/slp.html 

Product Details

• Amazon Sales Rank: #47825 in Books
• Published on: 2008-08-21
• Original language: English
• Binding: Paperback
• 1024 pages

About the Author

Dan Jurafsky is an associate professor in the Department of Linguistics, and by courtesy in Department of Computer Science, at Stanford University. Previously, he was on the faculty of the University of Colorado, Boulder, in the Linguistics and Computer Science departments and the Institute of Cognitive Science. He was born in Yonkers, New York, and received a B.A. in Linguistics in 1983 and a Ph.D. in Computer Science in 1992, both from the University of California at Berkeley. He received the National Science Foundation CAREER award in 1998 and the MacArthur Fellowship in 2002. He has published over 90 papers on a wide range of topics in speech and language processing.

James H. Martin is a professor in the Department of Computer Science and in the Department of Linguistics, and a fellow in the Institute of Cognitive Science at the University of Colorado at Boulder. He was born in New York City, received a B.S. in Comoputer Science from Columbia University in 1981 and a Ph.D. in Computer Science from the University of California at Berkeley in  1988. He has authored over 70 publications in computer science including the book A Computational Model of Metaphor Interpretation.

Customer Reviews

the best introduction to the field
This is the basic text for my master's course in Speech and Language Processing. It is used in several classes, though as the only text in the natural language processing class, which is clearly its strength. We also use it in the speech processing class, but it does need supplemental material here. If you are looking for a introduction to speech and language processing, you can't find a better book, and with a reasonable price at that.

Specifically, the book covers natural language processing, computational linguistics and speech recognition. There is also a chapter dealing with speech synthesis, and another on machine translation. As a reminder of the important of linguistics in this field, even though it largely transcends it, the book is organised into four topical sections with several chapters each: Words, Syntax, Semantics and Pragmatics.

The Words section includes chapters which introduce regular expressions, finite-state transducers, (computational) phonology, text-to-speech synthesis, probabilistic models of pronunciation and spelling, n-grams, and finally hidden Markov models (HMMs) and speech recognition. The Syntax section introduces word classes and part-of-speech tagging, context-free grammars, parsing, features and unification. The Semantics section has chapters on meaning representation, semantic analysis, lexical semantics, word sense disambiguation and information retrieval. Finally, the Pragmatics section covers discourse, dialogue, conversational agents, natural language generation and machine translation.

Apart from (lots of) typos, this remains the best around
I finished a degree in computational linguistics last year and if it had not been for the scope and detail of this superb book I would have been completely lost. The authors can write well too - an entertaining text book would you believe?

A word of warning. There are some basic errors in the mathematical expositions - which are careless and should have been ironed out. There is fairly good errata online, but it does pay to be wary about just blankly copying some of the maths. Keeps you on your toes!

Those problems aside, there are so many goodies in this book that it cannot fail to get 5 stars. If you are doing any language processing, or you are embroiled in a semester long course, buy this book and save yourself a lot of grief.

Excellent all rounder
Doing a thesis on NLP, and checked this books out of the university library. Everything that one could want to know about linguistics, NLP, machine translation, it is all in here.

Thouroughly recommended.