Statistical Language Learning

by Eugene Charniak

Eugene Charniak breaks new ground in artificial intelligenceresearch by presentingstatistical language processing from an artificial intelligence point of view in a text forresearchers and scientists with a traditional computer science background.New, exacting empiricalmethods are needed to break the deadlock in such areas of artificial intelligence as robotics,knowledge representation, machine learning, machine translation, and natural language processing(NLP). It is time, Charniak observes, to switch paradigms. This text introduces statistical languageprocessing techniques ;word tagging, parsing with probabilistic context free grammars, grammarinduction, syntactic disambiguation, semantic wordclasses, word-sense disambiguation ;along with theunderlying mathematics and chapter exercises.Charniak points out that as a method of attacking NLPproblems, the statistical approach has several advantages. It is grounded in real text and thereforepromises to produce usable results, and it offers an obvious way to approach "one simplygathers statistics."Language, Speech, and Communication

Genres: Linguistics, Computer Science, Mathematics, Science, Reference

192 pages, Hardcover

First published January 4, 1994

About the author

Eugene Charniak is Professor of Computer Science at Brown University. He is the author of Statistical Language Learning (MIT Press) and other books.

Reviews

[David · Rating 4 out of 5]

There are more complete textbooks now that cover everything in this book in more detail, but this was one of the first entries in the field, and contains concise explanations of basic statistical language modeling, introducing you to n-grams, Hidden Markov Models, Probabilistic Context Free Grammars, and so on. It also has the advantage of being a very small paperback, if you want a light reference to carry around with you.