Table of Contents

Part 1 The Standard Model: Two Technologies; Morphology and Knowledge of Words; Syntax and Context-Free Grammars; Chart Parsing; Meaning and Semantic Processing; Exercises. Part 2 Statistical Models and the Entropy of English: A Fragment of Probability Theory; Statistical Models; Speech Recognition; Entropy; Markov Chains; Cross Entropy; Cross Entropy as a Model Evaluator; Exercises. Part 3 Hidden Markov Models and Two Applications: Trigram Models of English; Hidden Markov Models; Part-of-Speech Tagging; Exercises. Part 4 Algorithms for Hidden Markov Models: Finding the Most Likely Path; Computing HMM Output Probabilities; HMM Training; Exercises. Part 5 Probabilistic Context-Free Grammars: Probabilistic Grammars; PCFGs and Syntactic Ambiguity; PCFGs and Grammar Induction; PCFGs and Ungrammaticality; PCFGs and Language Modelling; Basic Algorithms for PCFGs; Exercises. Part 6 The Mathematics of PCFGs: Relation of HMMs to PCFGs; Finding Sentence Probabilities for PCFGs; Training PCFGs; Exercises. Part 7 Learning Probabilistic Grammars: Why the Simple Approach Fails; Learning Dependency Grammars; Learning from a Bracketed Corpus; Improving a Partial Grammar; Exercises. Part 8 Syntactic Disambiguation: Simple Methods for Prepositional Phrases; Using Semantic Information; Relative-Clause Attachment; Uniform Use of Lexical/Semantic Information; Exercises. Part 9 Word Classes and Meaning: Clustering; Clustering by Next Word; Clustering with Syntactic Information; Problems with Word Clustering; Exercises. Part 10 Word Senses and Their Disambiguation: Word Senses Using Outside Information; Word Senses Without Outside Information; Meanings and Selectional Restrictions; Discussion; Exercises.

Promotional Information

"This is a lovely book." -- David Nye

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

"This is a lovely book." -- David Nye