Show Summary Details

Page of

PRINTED FROM OXFORD HANDBOOKS ONLINE ( © Oxford University Press, 2018. All Rights Reserved. Under the terms of the licence agreement, an individual user may print out a PDF of a single chapter of a title in Oxford Handbooks Online for personal use (for details see Privacy Policy and Legal Notice).

date: 26 January 2020

Abstract and Keywords

Dictionary data was extensively exploited for research in natural language processing (NLP) in the 1980s and early 1990s. But interest has declined markedly since then, for a number of reasons: (1) Machine-readable dictionaries have proved difficult to parse efficiently for computational purposes. (2) Corpus-based statistical NLP has overtaken knowledge-based NLP for many applications. (3) Purpose-built lexical resources have proved more appropriate than dictionaries for many NLP tasks. (4) WordNet and similar ontologies are more computationally tractable, do a better job of modelling the lexicon as a system, and are more readily integrated with other components of a NLP system and with other knowledge bases. (5) Issues around intellectual property have isolated dictionaries from wider infrastructures of linguistic data. In spite of these problems, dictionary data remains useful as a supplementary resource; but this depends on more open licensing and on making dictionaries more interoperable with other resources.

Keywords: natural language processing, word sense disambiguation, word sense induction, ontologies, directed graphs, WordNet, Linked Data, statistical NLP, symbolic NLP

Access to the complete content on Oxford Handbooks Online requires a subscription or purchase. Public users are able to search the site and view the abstracts and keywords for each book and chapter without a subscription.

Please subscribe or login to access full text content.

If you have purchased a print title that contains an access token, please see the token for information about how to register your code.

For questions on access or troubleshooting, please check our FAQs, and if you can''t find the answer there, please contact us.