本书的主要思路就是将已经分析过的语料库变成一个句法知识库，从中提取短语结构语法规则，并通过基于实例的手段，在知识库中为待分析语句提取一棵最佳句法树。本书对上述各个部分的研究进行了详细的描述，对系统的实际表现进行了深入的量化评测，并有专门章节来探讨句法分析的评测问题。除此之外，还探讨了介词短语的自动分析，特别是这类短语的句法功能的自动判定，因为这一研究和句法相似度分析有着密切的关系。同时，本书还就自动语法分析在语音合成及语音识别中的应用做了相应的介绍和说明，希望对读者能有所帮助。

语料库语言学和计算语言学为促进自然语言处理技术快速发展的两门基础学科。《英语语料库与自动语法分析》系这两个领域的一本专著，它以国际英语语料库为背景，着重探讨大型语料库的语法分析，尤其是英语口语材料给计算机自动处理带来的一系列难题。书中涉及基于概率的自动词类识别和基于实例的自动句法分析这两大技术，并有专门章节来探讨句法分析的评测问题，对AUTASYS和The Survey Parser这两个软件系统的实际表现进行了深入的量化评测。此外，本书还探讨了介词短语的自动分析，特别是这类短语的句法功能的自动判定，并对自动语法分析在语音合成及语音识别中的应用做了相应的说明。

Preface

前言

List of Figures

List of Tables

Abstract

1. Introduction

 1.1. What is Parsing?

 1.2. The Introspective View

 1.3. The Retrospective View

 1.4. Data-Oriented Parsing

 1.5. General Problems

 1.6. The Proposed Research

1.6.1. Background to the Proposed Research

1.6.2. The Basic Approach of the Proposed Research

1.6.3. The Strengths and Novelties of the Proposed Approach

 1.6.3.1. Automated Grammar Generation

 1.6.3.2. De-Lexicalised Terminal Nodes

 1.6.3.3. Global Parse with Subcategorisation Features

 1.6.3.4. High-Quality Partial Parse

 1.6.3.5. Intrinsic Ability to Learn

 1.7. The Organisation of the Book

2. The Automatic Analysis of English Word Classes

 2.1. An Overview of Word Class Tagging

 2.2. Major Word Class Tagging Schemes

2.2.1. The Lancaster-Oslo/Bergen Tagging Scheme

 2.2.1.1. The Lancaster-Oslo-Bergen Corpus

 2.2.1.2. The Lancaster-Oslo-Bergen Tag Set

 2.2.1.3. Summary

2.2.2. The International Corpus of English Tagging Scheme

 2.2.2.1. The International Corpus of English

 2.2.2.2. The International Corpus of English Tag Set

2.2.3. A Comparison of LOB and ICE

 2.3. Word Class Tagging Methodologies

2.3.1. The Rule-Based Approach

2.3.2. The Probabilistic Approach

 2.4. AUTASYS: A Hybrid Tagging System

2.4.1. A Probabilistic Approach Using the LOB Tag Set

 2.4.1.1. The Tag Assignment Module

  2.4.1.1.1. Tokenisation

  2.4.1.1.2. The treatment of"."

  2.4.1.1.3. The treatment of"'"

  2.4.1.1.4. Sentence boundary markers

 2.4.1.2. Orthographic Analysis

 2.4.1.3. Lexicon Lookup

  2.4.1.3.1. The lexicon

  2.4.1.3.2. The coverage of the lexicon

 2.4.1.4. Morphological Analysis

2.4.2. The Idiom Identification Module

2.4.3. The Probabilistic Tag Selection Module

 2.4.3.1. The Bigram Probabilistic Matrix

 2.4.3.2. Implementing Probabilistic Tag Selection

2.4.4. The Rule-Based Refinement Module

2.4.5. Empirical Evaluation

2.4.6. Permissive AUTASYS-LOB Disagreements

2.4.6.1. NNP-NPT

2.4.6.2. JJ-JJB

2.4.6.3. NNP-NPL

2.4.6.4. RB-NN

2.4.7. Summary

 2.5. A Rule-Based Approach towards LOB to ICE Translation

2.5.1. Solutions for Verbs

 2.5.1.1. Auxiliary vs. Lexical

 2.5.1.2. Monotransitive vs. Complex Transitive

 2.5.1.3. Finite vs. Nonfinite

2.5.2. Closed Sets

2.5.3. Initial Results

2.5.4. Problems

2.5.5. Summary

3. The Automatic Induction of a Formal Grammar

 3.1. Introduction

 3.2. The ICE Parsing Scheme

 3.3. Grammar Generation

3.3.1. Phrase Structure Rules

3.3.2. Phrase Structure Cluster Rules

 3.4. Evaluating the Coverage

3.4.1. The Construction of the Training and Test Sets

3.4.2. The Number of Extracted Rules

3.4.3. The Coverage of Adjective Phrase Rules

3.4.4. The Coverage of Adverb Phrase Rules

3.4.5. The Coverage of Noun Phrase Rules

3.4.6. The Coverage of Verb Phrase Rules

3.4.7. The Coverage of Prepositional Phrase Rules

3.4.8. The Coverage of Phrase Structure Cluster Rules

3.4.9. Discussion

4. Robust Practical Analogy-Based Parsing

 4.1. Introduction

4.1.1. Analogy-Based Parsing

 4.2. An Overview of the Survey Parser

 4.3. The Construction of the Syntactic Knowledge Base

4.3.1. Phrase Structure Rules

4.3.2. Phrase Structure Cluster Rules

 4.3.2.1. Feature Constraints

 4.3.2.2. Nonobligatory Elements

 4.3.2.3. A Definition of Analogy

 4.4. Parsing with Phrase Structure and Phrase Structure Cluster Rules

4.4.1. The Analysis of Word Classes

4.4.2. The Analysis of Phrases

4.4.3. The Analysis of Clauses

 4.4.3.1. Partial Analysis

 4.5. Some Initial Evaluation

4.5.1. Evaluating the Coverage of Phrase Structure Rules

4.5.2. Evaluating the Coverage of Phrase Structure Cluster Rules

4.5.3. Evaluating the Labelling Precision

4.5.4. Evaluating the Accuracy of Analysis

4.5.5. Evaluating the Processing Speed

 4.6. Concluding Remarks

5. Extensive Evaluations of the Survey Parser

 5.1. Introduction

 5.2. Commonly Used Metrics

5.2.1. Labelled Match

5.2.2. Bracketed Match

5.2.3. Crossing-Brackets Rate

5.2.4. Summary

 5.3. Evaluations with the NIST Scheme

5.3.1. Labelling Accuracy

 5.3.1.1. Methodology

 5.3.1.2. Evaluating the Scoring Program

 5.3.1.3. Evaluating the Labelling Accuracy of Parser Produced Trees

5.3.2. Bracketing Accuracy

 5.3.2.1. A Linear Representation of the Hierarchical Structure

 5.3.2.2. Evaluating the Scoring Program

 5.3.2.3. Evaluating the Bracketing Accuracy of Parser Produced Trees

  5.3.3. Labelling and Bracketing Accuracy Scores Combined

 5.3.3.1. A Description

 5.3.3.2. Empirical Scores by the Survey Parser

 5.3.3.3. A Comparison with other Reports

   5.3.3.3.1. A Comparison with Keller (2003)

   5.3.3.3.2. A Comparison with Plaehn (2004)

   5.3.3.3.3. A Comparison with Henderson (2004)

   5.3.3.3.4. Summary

 5.4. Summary

6. The Resolution of Prepositional Phrases

 6.1. Introduction

 6.2. PPs in Contemporary British English

6.2.1. Prepositions

6.2.2. Prepositional Complement

6.2.3. The Syntactic Functions of Prepositional Phrases

 6.3. Data and Resources Used in the Experiment

 6.4. Scope of Experiment

 6.5. Test Data

 6.6. Lexical Database

 6.7. Rules and their Coverage

6.7.1. Prepositional Phrases as Adjective Phrase Postmodifiers

 6.7.1.1. Test Data

 6.7.1.2. Attachment Rules

 6.7.1.3. Morphological Analysis

 6.7.1.4. Coverage

6.7.2. Prepositional Phrases as Noun Phrase Postmodifiers

 6.7.2.1. Test Data

 6.7.2.2. Attachment Rules

 6.7.2.3. Morphological Analysis

 6.7.2.4. Coverage of the Rules

6.7.3. Prepositional Phrases as Adverbials

 6.8. Overall Success Rate and Discussion

7. Conclusions and Further Work

 7.1. Conclusions

 7.2. Applications of AUTASYS and the Survey Parser

7.2.1. AUTASYS

7.2.2. The Survey Parser

 7.2.2.1. SpeechMaker

 7.2.2.2. Correlation between Tone Units and Syntax

7.3. Future Work

  7.3.1. Implementation of Automated Prepositional Phrase Attachment

  7.3.2. Automated Clause Boundary Detection and Attachment

References

Appendix A: A List of LOB Tags

Appendix B: A List of ICE Tags

Appendix C: A List of AUTASYS Idioms

Appendix D: A List of ICE Parsing Symbols

Appendix E: A List of ICE Prepositions in Descending Frequency Order

Appendix F: A Distributional Profile of ICE-GB Prepositions

Index