Statistical Language Learning / Edition 1

Statistical Language Learning / Edition 1

by Eugene Charniak, Charniak
     
 

ISBN-10: 0262531410

ISBN-13: 9780262531412

Pub. Date: 08/26/1996

Publisher: MIT Press

Eugene Charniak breaks new ground in artificial intelligenceresearch 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,

…  See more details below

Overview

Eugene Charniak breaks new ground in artificial intelligenceresearch 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 wordclasses,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

Read More

Product Details

ISBN-13:
9780262531412
Publisher:
MIT Press
Publication date:
08/26/1996
Series:
Language, Speech, and Communication
Edition description:
Reprint
Pages:
190
Product dimensions:
5.90(w) x 8.80(h) x 0.40(d)
Age Range:
18 Years

Table of Contents

List of Figures ..... xii
Preface ..... xvii1 The Standard Model ..... 1
1.1 Two Technologies ..... 1
1.2 Morphology and Knowledge of Words ..... 2
1.3 Syntax and Context-Free Grammars ..... 4
1.4 Chart Parsing ..... 9
1.5 Meaning and Semantic Processing ..... 16
1.6 Exercises ..... 19
2 Statistical Models and the Entropy of English ..... 21
2.1 A Fragment of Probability Theory ..... 21
2.2 Statistical Models ..... 24
2.3 Speech Recognition ..... 26
2.4 Entropy ..... 27
2.5 Markov Chains ..... 32
2.6 Cross Entropy ..... 32
2.7 Cross Entropy as a Model Evaluator ..... 34
2.8 Exercises ..... 37
3 Hidden Markov Models and Two Applications ..... 39
3.1 Trigram Models of English ..... 39
3.2 Hidden Markov Models ..... 43
3.3 Part-of-Speech Tagging ..... 45
3.4 Exercises ..... 51
4 Algorithms for Hidden Markov Models ..... 53
4.1 Finding the Most Likely Path ..... 53
4.2 Computing HMM Output Probabilities ..... 57
4.3 HMM Training ..... 61
4.4 Exercises ..... 70
5 Probabilistic Context-Free Grammars ..... 75
5.1 Probabilistic Grammars ..... 75
5.2 PCFG and Syntactic Ambiguity ..... 79
5.3 PCFG and Grammar Induction ..... 80
5.4 PCFG and Ungrammaticality ..... 82
5.5 PCFG and Language Modeling ..... 83
5.6 Basic Algorithms for PCFGs ..... 85
5.7 Exercises ..... 86
6 The Mathematics of PCFGs ..... 87
6.1 Relation of HMMs to PCFGs ..... 87
6.2 Finding Sentence Probabilities for PCFGs ..... 89
6.3 Training PCFGs ..... 97
6.4 Exercises ..... 100
7 Learning Probabilistic Grammars ..... 103
7.1Why the Simple Approach Fails ..... 103
7.2 Learning Dependency Grammars ..... 105
7.3 Learning from a Bracketed Corpus ..... 108
7.4 Improving a Partial Grammar ..... 111
7.5 Exercises ..... 116
8 Syntactic Disambiguation ..... 119
8.1 Simple Methods for Prepositional Phrases ..... 119
8.2 Using Semantic Information ..... 123
8.3 Relative-Clause Attachment ..... 126
8.4 Uniform Use of Lexical/Semantic Information ..... 129
8.5 Exercises ..... 135
9 Word Classes and Meaning ..... 135
9.1 Clustering ..... 135
9.2 Clustering by Next word ..... 136
9.3 Clustering with Syntactic Information ..... 139
9.4 Problems with word Clustering ..... 144
9.5 Exercises ..... 145
10 Word Senses and Their Disambiguation ..... 147
10.1 Word Senses Using Outside Information ..... 147
10.2 Word Senses Without Outside Information ..... 151
10.3 Meanings and Selectional Restrictions ..... 155
10.4 Discussion ..... 159
10.5 Exercises ..... 162
Bibliography ..... 163
Glossary ..... 165
Index ..... 167

Read More

Customer Reviews

Average Review:

Write a Review

and post it to your social network

     

Most Helpful Customer Reviews

See all customer reviews >