Seretan Syntax-Based Collocation Extraction

1. Auflage 2011
ISBN: 978-94-007-0134-2
Verlag: Springer Netherlands
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, Band 44, 220 Seiten

Reihe: Text, Speech and Language Technology

Syntax-Based Collocation Extraction is the first book to offer a comprehensive, up-to-date review of the theoretical and applied work on word collocations. Backed by solid theoretical results, the computational experiments described based on data in four languages provide support for the book's basic argument for using syntax-driven extraction as an alternative to the current cooccurrence-based extraction techniques to efficiently extract collocational data. The work described in Syntax-Based Collocation Extraction focuses on using linguistic tools for corpus-based identification of collocations. It takes advantage of recent advances in parsing to propose a novel deep syntactic analytic collocation extraction that has applicability to a range of important core tasks in Computational Linguistics. The book is useful for anyone interested in computational analysis of texts, collocation phenomena, and multi-word expressions in general.

Autoren/Hrsg.

Seretan, Violeta

Inhaltsverzeichnis

1;Preface;7
2;Contents;8
3; 1 Introduction;11
3.1;1.1 Collocations and Their Relevance for NLP;11
3.2;1.2 The Need for Syntax-Based Collocation Extraction;13
3.3;1.3 Aims;14
3.4;1.4 Chapters Outline;16
4; 2 On Collocations;18
4.1;2.1 Introduction;18
4.2;2.2 A Survey of Definitions;19
4.2.1;2.2.1 Statistical Approaches;20
4.2.2;2.2.2 Linguistic Approaches;21
4.2.3;2.2.3 Collocation vs. Co-occurrence;22
4.3;2.3 Towards a Core Collocation Concept;23
4.4;2.4 Theoretical Perspectives on Collocations;26
4.4.1;2.4.1 Contextualism;26
4.4.2;2.4.2 Text Cohesion;27
4.4.3;2.4.3 Meaning-Text Theory;28
4.4.4;2.4.4 Semantics and Metaphoricity;29
4.4.5;2.4.5 Lexis-Grammar Interface;30
4.5;2.5 Linguistic Descriptions;31
4.5.1;2.5.1 Semantic Compositionality;31
4.5.2;2.5.2 Morpho-Syntactic Characterisation;33
4.6;2.6 What Collocation Means in This Book;35
4.7;2.7 Summary;36
5; 3 Survey of Extraction Methods;38
5.1;3.1 Introduction;38
5.2;3.2 Extraction Techniques;38
5.2.1;3.2.1 Collocation Features Modelled;38
5.2.2;3.2.2 General Extraction Architecture;40
5.2.3;3.2.3 Contingency Tables;41
5.2.4;3.2.4 Association Measures;43
5.2.5;3.2.5 Criteria for the Application of Association Measures;51
5.3;3.3 Linguistic Preprocessing;53
5.3.1;3.3.1 Lemmatization;53
5.3.2;3.3.2 POS Tagging;54
5.3.3;3.3.3 Shallow and Deep Parsing;56
5.3.4;3.3.4 Beyond Parsing;57
5.4;3.4 Survey of the State of the Art;58
5.4.1;3.4.1 English;59
5.4.2;3.4.2 German;60
5.4.3;3.4.3 French;63
5.4.4;3.4.4 Other Languages;65
5.5;3.5 Summary;67
6; 4 Syntax-Based Extraction;68
6.1;4.1 Introduction;68
6.2;4.2 The Fips Multilingual Parser;71
6.3;4.3 Extraction Method;74
6.3.1;4.3.1 Candidate Identification;74
6.3.2;4.3.2 Candidate Ranking;77
6.4;4.4 Evaluation;78
6.4.1;4.4.1 On Collocation Extraction Evaluation;78
6.4.2;4.4.2 Evaluation Method;81
6.4.3;4.4.3 Experiment 1: Monolingual Evaluation;84
6.4.4;4.4.4 Results of Experiment 1;88
6.4.5;4.4.5 Experiment 2: Cross-Lingual Evaluation;90
6.4.6;4.4.6 Results of Experiment 2;94
6.5;4.5 Qualitative Analysis;97
6.5.1;4.5.1 Error Analysis;98
6.5.2;4.5.2 Intersection and Rank Correlation;101
6.5.3;4.5.3 Instance-Level Analysis;103
6.6;4.6 Discussion;106
6.7;4.7 Summary;109
7; 5 Extensions;111
7.1;5.1 Identification of Complex Collocations;111
7.1.1;5.1.1 The Method;112
7.1.2;5.1.2 Experimental Results;115
7.1.3;5.1.3 Related Work;117
7.2;5.2 Data-Driven Induction of Syntactic Patterns;119
7.2.1;5.2.1 The Method;120
7.2.2;5.2.2 Experimental Results;121
7.2.3;5.2.3 Related Work;122
7.3;5.3 Corpus-Based Collocation Translation;124
7.3.1;5.3.1 The Method;124
7.3.2;5.3.2 Experimental Results;126
7.3.3;5.3.3 Related Work;128
7.4;5.4 Summary;129
8; 6 Conclusion;131
8.1;6.1 Main Contributions;131
8.2;6.2 Future Directions;133
9; A List of Collocation Dictionaries;136
9.1;English;136
9.2;French;136
9.3;Italian;136
9.4;Polish;137
9.5;Portugese;137
9.6;Russian;137
9.7;Spanish;137
10; B List of Collocation Definitions;138
11; C Association Measures -- Mathematical Notes;140
11.1;C.1 X2;140
11.2;C.2 Log-Likelihood Ratio;141
12;D Monolingual Evaluation (Experiment 1);142
12.1;D.1 Test Data and Annotations;142
12.2;D.2 Results;161
13;E Cross-Lingual Evaluation (Experiment 2);163
13.1;E.1 Test Data and Annotations;163
13.2;E.2 Results;201
14; F Output Comparison;203
15;References;205
16;Index;218