向心理论的参数设定及其在英汉指代消解中的应用研究
发布时间:2021-02-25 19:32
学者们对于回指研究的热情已经历经半个世纪而不衰,研究方法也涉及各种语言学理论的方方面面。指代消解研究起源于自然语言处理,其主要目的是使用计算机来为篇章中的回指语找到正确的指代对象。因其从计算语言学的角度着手,着重研究回指的生成和理解乃至篇章的理解,近年来成为回指研究的新方向,引起了不少学者的关注,但这方面的对比研究几乎还为空白,有待填补。指代消解研究所采用的理论框架是多种多样的,向心理论是其中的一种。在向心理论的基础上进行指代消解开创了指代消解的一个新局面,因为向心理论恰到好处地把语言学理论框架和计算机系统要求的可操作性结合在一起。向心理论描述了话语的注意焦点、指称方式的选择和语篇连贯性之间的关系,利用“中心”概念对语篇的连贯性和显著性进行解释,并为读者(听者)识别代词或名词词组的指称对象提供了三条制约条件和两条规则。其中制约条件三和规则一为语篇中的回指语提供了一个理想的消解模式。向心理论是二十世纪八十年代初由计算语言学领域的学者提出的,之后被广泛的应用于各种语言的指代消解和篇章处理中。本文选择该理论作为研究基础一是因为它在指代消解方面体现出的有效性,二是因为以向心理论为基础的对比框架...
【文章来源】:上海外国语大学上海市 211工程院校 教育部直属院校
【文章页数】:200 页
【学位级别】:博士
【文章目录】:
Acknowledgement
Abstract
摘要
Table of Contents
List of Tables
List of Figures
Chapter 1 Introduction
1.1 Motivations
1.2 Scope of the Study
1.3 Methodology , Hypotheses and Objectives of the Study
1.4 Organization of the Dissertation
Chapter 2 Centering Theory and Its Framework
2.1 Introduction
2.2 Origin and Development
2.2.1 Original Intuitions and Intentions
2.2.1.1 Focus
2.2.1.1.1 Grosz (1977)
2.2.1.1.2 Sidner (1979, 1981, 1983)
2.2.1.1.3 Grosz and Sidner (1985, 1986)
2.2.1.2 Center
2.2.2 Formulation
2.3 Framework
2.3.1 Terminology and Definition
2.3.1.1 Discourse Segment (D) and Utterance (U)
2.3.1.2 Centers, Forward-Looking Centers and Backward-Looking Centers
2.3.1.3 Ranking and Preferred Centers
2.3.1.4 Realization
2.3.2 Constraints and Rules
2.3.3 Basic Claims and Issues in Centering
2.3.3.1 Basic Claims
2.3.3.2 Local Coherence and Local Salience
2.3.3.2.1 Local Coherence
2.3.3.2.2 Local Salience
2.4 Centering as a Cross-linguistic and Language-specific Theory
2.5 Centering as a Parametric Theory
2.5.1 The Parameters of Centering
2.5.1.1 Utterance (Ui) and Previous Utterance (Ui-1)
2.5.1.2 Ranking
2.5.1.3 Rule 1 Pronouns
2.5.1.4 Realization
2.5.1.5 Discourse Segmentation
Chapter 3 Centering and Anaphora Resolution
3.1 Introduction
3.2 Influential Algorithms of Anaphora Resolution in Literature
3.2.1 Tree Search Algorithm / Hobbs’Algorithm
3.2.1.1 The Algorithm
3.2.1.2 Comments
3.2.2 RAP (Resolution of Anaphora Procedure)
3.2.2.1 Filters and Components in RAP
3.2.2.2 Algorithm in RAP
3.2.2.3 Comments
3.2.3 Robust, Knowledge-poor Approach
3.2.3.1 Working Mechanism
3.2.3.2 Comments
3.3 Strategies and Theories
3.3.1 Computing Strategies
3.3.2 Theoretical Framework
3.4 Centering Algorithms
3.4.1 BFP
3.4.1.1 Algorithm
3.4.1.2 Comments
3.4.2 LRC (Left-Right Centering Algorithm)
3.4.2.1 Algorithm
3.4.2.2 Comments
3.4.3 Optimization Theory
3.4.3.1 Algorithm
3.4.3.2 Comments
3.5 Algorithm Design in China
3.5.1 Centering-Based Algorithms
3.5.1.1 Yeh and Chen (2001, 2003)
3.5.1.1.1 Algorithms
3.5.1.1.2 Comments
3.5.1.2 Wang (2004)
3.5.1.2.1 Algorithms
3.5.1.2.2 Comments
3.5.1.3 Xu, Duan and Fu (2006, 2008, 2009)
3.5.1.3.1 Algorithms
3.5.1.3.2 Comments
Chapter 4 Methodology of the Present Study
4.1 Introduction
4.2 Poesio’s Empirical Study of Parametric Centering
4.2.1 Parameter Setting
4.2.2 Annotation of Corpus
4.2.2.1 Utterance
4.2.2.2 NPs
4.2.2.3 Anaphoric Information
4.2.2.4 Segmentation
4.2.3 Results and Enlightenment
4.2.3.1 Utterance
4.2.3.2 Realization
4.2.3.3 Segmentation
4.2.3.4 Ranking
4.2.3.5 Rule-1 Pronoun
4.2.3.6 Difference Between Domains
4.3 Contrastive Evaluation of Centering Parameters
4.3.1. Segmentation
4.3.2 Rule-1 Pronouns
4.3.3 Utterance
4.3.4 Realization
4.3.5 Ranking
4.3.5.1 Theoretical Basis
4.3.5.2 Topic in Chinese
4.3.5.3.R anking Scale by Grammatical Roles in our Research
4.3.5.4 Other Means of Ranking
Chapter 5 Corpus and Annotation
5.1 Introduction
5.2 Corpus
5.3 Annotation
5.3.1 Basis of Annotation: Penn Treebank
5.3.2 Adaptation to Our Study
5.3.2.1 Noun Phrase
5.3.2.1.1 NP Types
5.3.2.1.2 Grammatical and Morphological Information
5.3.2.2 Grammatical Roles
5.3.2.3 Hierarchical Structures
5.3.2.4 Reference Types
5.3.2.5 Positions of Antecedents and database
5.3.3 Open Issues in Annotation
5.3.3.1 Coordinated NP
5.3.3.2 “It”as Surface Subject
5.3.3.3 Special Sentence Patterns
Chapter 6 Algorithms in our Research
6.1 Introduction
6.2 Guiding Principles
6.2.1 Eliminating Principles
6.2.1.1 Morphological Filter
6.2.1.2 Syntactic Filter
6.2.1.3 Inaccessibility Inheritance Principle
6.2.2 Preference Principles
6.3 Algorithms in our Study
6.3.1 Inter-algorithm Operating Procedure
6.3.2 Inner-algorithm Operating Procedure
6.3.3 Algorithms and their Structure in our research
6.3.3.1 Alg.1 Lin
6.3.3.2 Alg.2 Grm
6.3.3.3 Alg.3 Para
6.3.3.4 Alg.4 Cb
6.3.3.5 Alg.5 Para +Cb
6.3.3.6 Alg.6 Sub
Chapter 7 Results Analysis and Discussion
7.1 Introduction
7.2 Preliminaries
7.2.1 Statistical Overview of the Corpus
7.2.2 Terms: Recall, Success and Precision Rates
7.2.3 Other Abbreviations
7.3 Results in Terms of Utterance
7.3.1 Chinese
7.3.2 English
7.4 Results in Terms of Rule-1 Pronouns
7.4.1 Chinese
7.4.2 English
7.5 Results in Terms of Ranking
7.5.1 Linear Order
7.5.2 Grammatical Function
7.5.3 Other Factors Coupled with Grammatical Function
7.5.3.1 Chinese
7.5.3.2 English
7.5.4 Main/Surbordinate Hierarchy
7.5.4.1 Chinese
7.5.4.2 English
7.6 Results in Terms of Zero Topic (Subject)
Chapter 8 Conclusion
8.1 Summary of Major Findings
8.2 Theoretical and Practical Implications of the Study
8.3 Limitations of the Study and Suggestions for Future Research
References
Appendix Ⅰ Sample of Annotated Chinese Corpus
Appendix Ⅱ Sample of Annotated English Corpus
Appendix Ⅲ Interface for Database Information Input
Appendix Ⅳ Resolution Results of Chinese Corpus
Appendix Ⅴ Resolution Results of English Corpus
【参考文献】:
期刊论文
[1]零形式和零成分的确立条件[J]. 袁毓林. 当代语言学. 2010(03)
[2]前瞻中心的排序对指代消解的影响——一项向心理论参数化实证研究[J]. 段嫚娟,许余龙,付相君. 外国语(上海外国语大学学报). 2009(03)
[3]向心理论的参数化研究[J]. 许余龙. 当代语言学. 2008(03)
[4]“语句”与“代词”的设定对指代消解的影响——一项向心理论参数化实证研究[J]. 许余龙,段嫚娟,付相君. 现代外语. 2008(02)
[5]中心理论和回指解析计算法[J]. 刘礼进. 外语学刊. 2005(06)
[6]汉语零形回指解析——基于向心理论的研究[J]. 王德亮. 现代外语. 2004(04)
[7]语篇向心理论述评[J]. 苗兴伟. 当代语言学. 2003(02)
[8]语篇回指的认知语言学研究与验证[J]. 许余龙. 外国语(上海外国语大学学报). 2003(02)
[9]语篇回指的认知语言学探索[J]. 许余龙. 外国语(上海外国语大学学报). 2002(01)
[10]Referring Expressions: A Unified Approach[J]. K.M. Jaszczolt. 外国语(上海外国语大学学报). 2001(02)
本文编号:3051469
【文章来源】:上海外国语大学上海市 211工程院校 教育部直属院校
【文章页数】:200 页
【学位级别】:博士
【文章目录】:
Acknowledgement
Abstract
摘要
Table of Contents
List of Tables
List of Figures
Chapter 1 Introduction
1.1 Motivations
1.2 Scope of the Study
1.3 Methodology , Hypotheses and Objectives of the Study
1.4 Organization of the Dissertation
Chapter 2 Centering Theory and Its Framework
2.1 Introduction
2.2 Origin and Development
2.2.1 Original Intuitions and Intentions
2.2.1.1 Focus
2.2.1.1.1 Grosz (1977)
2.2.1.1.2 Sidner (1979, 1981, 1983)
2.2.1.1.3 Grosz and Sidner (1985, 1986)
2.2.1.2 Center
2.2.2 Formulation
2.3 Framework
2.3.1 Terminology and Definition
2.3.1.1 Discourse Segment (D) and Utterance (U)
2.3.1.2 Centers, Forward-Looking Centers and Backward-Looking Centers
2.3.1.3 Ranking and Preferred Centers
2.3.1.4 Realization
2.3.2 Constraints and Rules
2.3.3 Basic Claims and Issues in Centering
2.3.3.1 Basic Claims
2.3.3.2 Local Coherence and Local Salience
2.3.3.2.1 Local Coherence
2.3.3.2.2 Local Salience
2.4 Centering as a Cross-linguistic and Language-specific Theory
2.5 Centering as a Parametric Theory
2.5.1 The Parameters of Centering
2.5.1.1 Utterance (Ui) and Previous Utterance (Ui-1)
2.5.1.2 Ranking
2.5.1.3 Rule 1 Pronouns
2.5.1.4 Realization
2.5.1.5 Discourse Segmentation
Chapter 3 Centering and Anaphora Resolution
3.1 Introduction
3.2 Influential Algorithms of Anaphora Resolution in Literature
3.2.1 Tree Search Algorithm / Hobbs’Algorithm
3.2.1.1 The Algorithm
3.2.1.2 Comments
3.2.2 RAP (Resolution of Anaphora Procedure)
3.2.2.1 Filters and Components in RAP
3.2.2.2 Algorithm in RAP
3.2.2.3 Comments
3.2.3 Robust, Knowledge-poor Approach
3.2.3.1 Working Mechanism
3.2.3.2 Comments
3.3 Strategies and Theories
3.3.1 Computing Strategies
3.3.2 Theoretical Framework
3.4 Centering Algorithms
3.4.1 BFP
3.4.1.1 Algorithm
3.4.1.2 Comments
3.4.2 LRC (Left-Right Centering Algorithm)
3.4.2.1 Algorithm
3.4.2.2 Comments
3.4.3 Optimization Theory
3.4.3.1 Algorithm
3.4.3.2 Comments
3.5 Algorithm Design in China
3.5.1 Centering-Based Algorithms
3.5.1.1 Yeh and Chen (2001, 2003)
3.5.1.1.1 Algorithms
3.5.1.1.2 Comments
3.5.1.2 Wang (2004)
3.5.1.2.1 Algorithms
3.5.1.2.2 Comments
3.5.1.3 Xu, Duan and Fu (2006, 2008, 2009)
3.5.1.3.1 Algorithms
3.5.1.3.2 Comments
Chapter 4 Methodology of the Present Study
4.1 Introduction
4.2 Poesio’s Empirical Study of Parametric Centering
4.2.1 Parameter Setting
4.2.2 Annotation of Corpus
4.2.2.1 Utterance
4.2.2.2 NPs
4.2.2.3 Anaphoric Information
4.2.2.4 Segmentation
4.2.3 Results and Enlightenment
4.2.3.1 Utterance
4.2.3.2 Realization
4.2.3.3 Segmentation
4.2.3.4 Ranking
4.2.3.5 Rule-1 Pronoun
4.2.3.6 Difference Between Domains
4.3 Contrastive Evaluation of Centering Parameters
4.3.1. Segmentation
4.3.2 Rule-1 Pronouns
4.3.3 Utterance
4.3.4 Realization
4.3.5 Ranking
4.3.5.1 Theoretical Basis
4.3.5.2 Topic in Chinese
4.3.5.3.R anking Scale by Grammatical Roles in our Research
4.3.5.4 Other Means of Ranking
Chapter 5 Corpus and Annotation
5.1 Introduction
5.2 Corpus
5.3 Annotation
5.3.1 Basis of Annotation: Penn Treebank
5.3.2 Adaptation to Our Study
5.3.2.1 Noun Phrase
5.3.2.1.1 NP Types
5.3.2.1.2 Grammatical and Morphological Information
5.3.2.2 Grammatical Roles
5.3.2.3 Hierarchical Structures
5.3.2.4 Reference Types
5.3.2.5 Positions of Antecedents and database
5.3.3 Open Issues in Annotation
5.3.3.1 Coordinated NP
5.3.3.2 “It”as Surface Subject
5.3.3.3 Special Sentence Patterns
Chapter 6 Algorithms in our Research
6.1 Introduction
6.2 Guiding Principles
6.2.1 Eliminating Principles
6.2.1.1 Morphological Filter
6.2.1.2 Syntactic Filter
6.2.1.3 Inaccessibility Inheritance Principle
6.2.2 Preference Principles
6.3 Algorithms in our Study
6.3.1 Inter-algorithm Operating Procedure
6.3.2 Inner-algorithm Operating Procedure
6.3.3 Algorithms and their Structure in our research
6.3.3.1 Alg.1 Lin
6.3.3.2 Alg.2 Grm
6.3.3.3 Alg.3 Para
6.3.3.4 Alg.4 Cb
6.3.3.5 Alg.5 Para +Cb
6.3.3.6 Alg.6 Sub
Chapter 7 Results Analysis and Discussion
7.1 Introduction
7.2 Preliminaries
7.2.1 Statistical Overview of the Corpus
7.2.2 Terms: Recall, Success and Precision Rates
7.2.3 Other Abbreviations
7.3 Results in Terms of Utterance
7.3.1 Chinese
7.3.2 English
7.4 Results in Terms of Rule-1 Pronouns
7.4.1 Chinese
7.4.2 English
7.5 Results in Terms of Ranking
7.5.1 Linear Order
7.5.2 Grammatical Function
7.5.3 Other Factors Coupled with Grammatical Function
7.5.3.1 Chinese
7.5.3.2 English
7.5.4 Main/Surbordinate Hierarchy
7.5.4.1 Chinese
7.5.4.2 English
7.6 Results in Terms of Zero Topic (Subject)
Chapter 8 Conclusion
8.1 Summary of Major Findings
8.2 Theoretical and Practical Implications of the Study
8.3 Limitations of the Study and Suggestions for Future Research
References
Appendix Ⅰ Sample of Annotated Chinese Corpus
Appendix Ⅱ Sample of Annotated English Corpus
Appendix Ⅲ Interface for Database Information Input
Appendix Ⅳ Resolution Results of Chinese Corpus
Appendix Ⅴ Resolution Results of English Corpus
【参考文献】:
期刊论文
[1]零形式和零成分的确立条件[J]. 袁毓林. 当代语言学. 2010(03)
[2]前瞻中心的排序对指代消解的影响——一项向心理论参数化实证研究[J]. 段嫚娟,许余龙,付相君. 外国语(上海外国语大学学报). 2009(03)
[3]向心理论的参数化研究[J]. 许余龙. 当代语言学. 2008(03)
[4]“语句”与“代词”的设定对指代消解的影响——一项向心理论参数化实证研究[J]. 许余龙,段嫚娟,付相君. 现代外语. 2008(02)
[5]中心理论和回指解析计算法[J]. 刘礼进. 外语学刊. 2005(06)
[6]汉语零形回指解析——基于向心理论的研究[J]. 王德亮. 现代外语. 2004(04)
[7]语篇向心理论述评[J]. 苗兴伟. 当代语言学. 2003(02)
[8]语篇回指的认知语言学研究与验证[J]. 许余龙. 外国语(上海外国语大学学报). 2003(02)
[9]语篇回指的认知语言学探索[J]. 许余龙. 外国语(上海外国语大学学报). 2002(01)
[10]Referring Expressions: A Unified Approach[J]. K.M. Jaszczolt. 外国语(上海外国语大学学报). 2001(02)
本文编号:3051469
本文链接:https://www.wllwen.com/wenyilunwen/yuyanyishu/3051469.html