Statistical Language Learning

Name: Statistical Language Learning
ISBN: 9780262032162

by Eugene Charniak · 1994

Eugene Charniak breaks new ground in artificial intelligence research by presenting statistical language processing from an artificial intelligence point of view in a text for researchers and scientists with a traditional computer science background. New, exacting empirical methods 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 language processing techniques — word tagging, parsing with probabilistic context free grammars, grammar induction, syntactic disambiguation, semantic word classes, word-sense disambiguation — along with the underlying mathematics and chapter exercises.

Charniak points out that as a method of attacking NLP problems, the statistical approach has several advantages. It is grounded in real text and therefore promises to produce usable results, and it offers an obvious way to approach learning: "one simply gathers statistics."

"Language, Speech, and Communication"

Click a tag to see books like this one that share it. Point at it (on a phone, tap it) for less of it instead.

Read it? Sign in to help tag it.

BuyAmazon Google Books

BorrowOpen Library A library near you

MoreCompare prices

Liked Statistical Language Learning? Here’s where I’d start.

These suit anyone who liked Statistical Language Learning. Sign in and mark a few books for picks shaped around your own taste.

Statistical Language Learning

Liked Statistical Language Learning? Here’s where I’d start.

“If you want more of the same, start with these.”

“If it was the linguistics that hooked you, try one of these.”

“These start from a similar idea, even if they go somewhere else with it.”