Syntax-Based Collocation Extraction [Paperback]

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 books 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.Collocation is a key language phenomenon which crucially impacts any text production task and which is exploitable in many text analysis tasks. This book offers a comprehensive and up-to-date review of the theoretical and practical work on this topic.1. Introduction .- 1.1 Collocations and Their Relevance for NLP . 1.2 The Need for Syntax-Based Collocation Extraction . 1.3 Aims . 1.4 Chapters Outline .- 2. On Collocations . 2.1. Introduction . 2.2 A Survey of Definitions . 2.3 Towards a Core Collocation Concept . 2.4 Theoretical Perspectives on Collocations . 2.5 Linguistic Descriptions . 2.6 What collocation means in this book . 2.7 Summary .- 3. Survey of Extraction Methods . 3.1 Introduction . 3.2 Extraction Techniques . 3.3 Linguistic Preprocessing . 3.4 Survey of the State of the Art . 3.5 Summary .- 4. Syntax-Based Extraction . 4.1 Introduction . 4.2 The Fips Multilingual Parser . 4.3 Extraction Method . 4.4 Evaluation . 4.5 Qualitative Analysis . 4.6 Discussion . 4.7 Summary .- 5. Extensions . 5.1 Identification of Complex CollocatilÃ'