Syntax Based Collocation Extraction

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.

This book re-examines the notion of word associations, more precisely collocations. It attempts to come to a potentially more generally applicable definition of collocation and how to best extract, identify and measure collocations. The book highlights the role played by (i) automatic linguistic annotation (part-of-speech tagging, syntactic parsing, etc.), (ii) using semantic criteria to facilitate the identification of collocations, (iii) multi-word structured, instead of the widespread assumption of bipartite collocational structures, for capturing the intricacies of the phenomenon of syntagmatic attraction, (iv) considering collocation and valency as near neighbours in the lexis-grammar continuum and (v) the mathematical properties of statistical association measures in the automatic extraction of collocations from corpora. This book is an ideal guide to the use of statistics in collocation analysis and lexicography, as well as a practical text to the development of skills in the application of computational lexicography. Lexical Collocation Analysis: Advances and Applications begins with a proposal for integrating both collocational and valency phenomena within the overarching theoretical framework of construction grammar. Next the book makes the case for integrating advances in syntactic parsing and in collocational analysis. Chapter 3 offers an innovative look at complementing corpus data and dictionaries in the identification of specific types of collocations consisting of restricted predicate-argument combinations. This strategy complements corpus collocational data with network analysis techniques applied to dictionary entries. Chapter 4 explains the potential of collocational graphs and networks both as a visualization tool and as an analytical technique. Chapter 5 introduces MERGE (Multi-word Expressions from the Recursive Grouping of Elements), a data-driven approach to the identification and extraction of multi-word expressions from corpora. Finally the book concludes with an analysis and evaluation of factors influencing the performance of collocation extraction methods in parsed corpora.

This book constitutes the refereed proceedings of the 14th China National Conference on Computational Linguistics, CCL 2014, and of the Third International Symposium on Natural Language Processing Based on Naturally Annotated Big Data, NLP-NABD 2015, held in Guangzhou, China, in November 2015. The 34 papers presented were carefully reviewed and selected from 283 submissions. The papers are organized in topical sections on lexical semantics and ontologies; semantics; sentiment analysis, opinion mining and text classification; machine translation; multilinguality in NLP; machine learning methods for NLP; knowledge graph and information extraction; discourse, coreference and pragmatics; information retrieval and question answering; social computing; NLP applications.

The ever-growing popularity of Google over the recent decade has required a specific method of man-machine communication: human query should be short, whereas the machine answer may take a form of a wide range of documents. This type of communication has triggered a rapid development in the domain of Information Extraction, aimed at providing the asker with a more precise information. The recent success of intelligent personal assistants supporting users in searching or even extracting information and answers from large collections of electronic documents signals the onset of a new era in man-machine communication – we shall soon explain to our small devices what we need to know and expect valuable answers quickly and automatically delivered. The progress of man-machine communication is accompanied by growth in the significance of applied Computational Linguistics – we need machines to understand much more from the language we speak naturally than it is the case of up-to-date search systems. Moreover, we need machine support in crossing language barriers that is necessary more and more often when facing the global character of the Web. This books reports on the latest developments in the field. It contains 15 chapters written by researchers who aim at making linguistic theories work – for the better understanding between the man and the machine.

The annual workshop on multiword expressions takes place since 2001 in conjunction with major computational linguistics conferences and attracts the attention of an ever-growing community working on a variety of languages, linguistic phenomena and related computational processing issues. MWE 2017 took place in Valencia, Spain, and represented a vibrant panorama of the current research landscape on the computational treatment of multiword expressions, featuring many high-quality submissions. Furthermore, MWE 2017 included the first shared task on multilingual identification of verbal multiword expressions. The shared task, with extended communal work, has developed important multilingual resources and mobilised several research groups in computational linguistics worldwide. This book contains extended versions of selected papers from the workshop. Authors worked hard to include detailed explanations, broader and deeper analyses, and new exciting results, which were thoroughly reviewed by an internationally renowned committee. We hope that this distinctly joint effort will provide a meaningful and useful snapshot of the multilingual state of the art in multiword expressions modelling and processing, and will be a point point of reference for future work.

The two-volume set LNCS 9623 + 9624 constitutes revised selected papers from the CICLing 2016 conference which took place in Konya, Turkey, in April 2016. The total of 89 papers presented in the two volumes was carefully reviewed and selected from 298 submissions. The book also contains 4 invited papers and a memorial paper on Adam Kilgarriff’s Legacy to Computational Linguistics. The papers are organized in the following topical sections: Part I: In memoriam of Adam Kilgarriff; general formalisms; embeddings, language modeling, and sequence labeling; lexical resources and terminology extraction; morphology and part-of-speech tagging; syntax and chunking; named entity recognition; word sense disambiguation and anaphora resolution; semantics, discourse, and dialog. Part II: machine translation and multilingualism; sentiment analysis, opinion mining, subjectivity, and social media; text classification and categorization; information extraction; and applications.

​This book is an excellent introduction to multiword expressions. It provides a unique, comprehensive and up-to-date overview of this exciting topic in computational linguistics. The first part describes the diversity and richness of multiword expressions, including many examples in several languages. These constructions are not only complex and arbitrary, but also much more frequent than one would guess, making them a real nightmare for natural language processing applications. The second part introduces a new generic framework for automatic acquisition of multiword expressions from texts. Furthermore, it describes the accompanying free software tool, the mwetoolkit, which comes in handy when looking for expressions in texts (regardless of the language). Evaluation is greatly emphasized, underlining the fact that results depend on parameters like corpus size, language, MWE type, etc. The last part contains solid experimental results and evaluates the mwetoolkit, demonstrating its usefulness for computer-assisted lexicography and machine translation. This is the first book to cover the whole pipeline of multiword expression acquisition in a single volume. It is addresses the needs of students and researchers in computational and theoretical linguistics, cognitive sciences, artificial intelligence and computer science. Its good balance between computational and linguistic views make it the perfect starting point for anyone interested in multiword expressions, language and text processing in general.

This book constitutes the refereed proceedings of the International Conference on Computational and Corpus-Based Phraseology, Europhras 2017, held in London, UK, in November 2017. The 31 full papers presented were carefully reviewed and selected from numerous submissions and are organized into the following thematic sessions: Phraseology in translation and contrastive studies, Lexicography and terminography, Exploitation of corpora in phraseological studies, Development of corpora for phraseological studies, Phraseology and language learning, Cognitive and cultural aspects of phraseology, Theoretical and descriptive approaches to phraseology, and Computational approaches to phraseology. The chapter 'Frequency Consolidation Among Word N-Grams' is available open access under a CC BY 4.0 license.