Statistical approaches to processing natural language text have become dominant in recent years. This foundational text is the first comprehensive introduction to statistical natural language processing (NLP) to appear. The book contains all the theory and algorithms needed for building NLP tools. It provides broad but rigorous coverage of mathematical and linguistic foundations, as well as detailed discussion of statistical methods, allowing students and researchers to construct their own implementations. The book covers collocation finding, word sense disambiguation, probabilistic parsing, information retrieval, and other applications.

I Preliminaries
1 Introduction 
1.1 Rationalist and Empiricist Approaches to Language 
1.2 Scientific Content 
1.3 The Ambiguity of Language: Why NLP Is Difficult 
1.4 Dirty Hands 
1.5 Further Reading 
1.6 Exercises

2 Mathematical Foundations 
2.1 Elementary Probability Theory 
2.2 Essential Information Theory 
2.3 Further Reading

3 Linguistics Essentials 
3.1 Parts of Speech and Morphology 
3.2 Phrase Structure 
3.3 Semantics and Pragmatics 
3.4 Other Areas 
3.5 Further Reading 
3.6 Exercises

4 Corpus-Based Work 
4.1 Getting Set Up 
4.2 Looking at Text 
4.3 Marked-Up Data 
4.4 Further Reading 
4.5 Exercises

II Words
5 Collocations 
5.1 Frequency 
5.2 Mean and Variance 
5.3 Hypothesis Testing 
5.4 Mutual Information 
5.5 The Notion of Collocation 
5.6 Further Reading

6 Statistical Inference: n-gram Models over Sparse Data 
6.1 Bins: Forming Equivalence Classes 
6.2 Statistical Estimators 
6.3 Combining Estimators 
6.4 Conclusions 
6.5 Further Reading 
6.6 Exercises

7 Word Sense Disambiguation 
7.1 Methodological Preliminaries 
7.2 Supervised Disambiguation 
7.3 Dictionary-Based Disambiguation 
7.4 Unsupervised Disambiguation 
7.5 What Is a Word Sense? 
7.6 Further Reading 
7.7 Exercises

8 Lexical Acquisition 
8.1 Evaluation Measures 
8.2 Verb Subcategorization 
8.3 Attachment Ambiguity 
8.4 Selectional Preferences 
8.5 Semantic Similarity 
8.6 The Role of Lexical Acquisition in Statistical NLP 
8.7 Further Reading

III Grammar
9 Markov Models 
9.1 Markov Models 
9.2 Hidden Markov Models 
9.3 The Three Fundamental Questions for HMMs 
9.4 HMMs: Implementation, Properties, and Variants 
9.5 Further Reading

10 Part-of-Speech Tagging 
10.1 The Information Sources in Tagging 
10.2 Markov Model Taggers 
10.3 Hidden Markov Model Taggers 
10.4 Transformation-Based Learning of Tags 
10.5 Other Methods, Other Languages 
10.6 Tagging Accuracy and Uses of Taggers 
10.7 Further Reading 
10.8 Exercises

11 Probabilistic Context Free Grammars 
11.1 Some Features of PCFGs 
11.2 Questions for PCFGs 
11.3 The Probability of a String 
11.4 Problems with the Inside-Outside Algorithm 
11.5 Further Reading 
11.6 Exercises

12 Probabilistic Parsing 
12.1 Some Concepts 
12.2 Some Approaches 
12.3 Further Reading 
12.4 Exercises

IV Applications and Techniques
13 Statistical Alignment and Machine Translation 
13.1 Text Alignment 
13.2 Word Alignment 
13.3 Statistical Machine Translation 
13.4 Further Reading

14 Clustering 
14.1 Hierarchical Clustering 
14.2 Non-Hierarchical Clustering 
14.3 Further Reading 
14.4 Exercises

15 Topics in Information Retrieval 
15.1 Some Background on Information Retrieval 
15.2 The Vector Space Models 
15.3 Term Distribution Models 
15.4 Latent Semantic Indexing 
15.5 Discourse Segmentation 
15.6 Further Reading 
15.7 Exercises

16 Text Categorization 
16.1 Decision Trees 
16.2 Maximum Entropy Modeling 
16.3 Perceptrons 
16.4 k Nearest Neighbor Classification 
16.5 Further Reading 
 

Christopher D. Manning is Assistant Professor in the Department of Computer Science at Stanford University. 

Hinrich Schotze is on the Research Staff at the Xerox Palo Alto Research Center.

배송정보

교환/반품 정보