A Uniform Approach to Analogies, Synonyms, Antonyms, and Associations

Simple item page
dc.creatorTurney, Peter D.
dc.date2008-08-31
dc.date.accessioned2026-07-07T09:59:40Z
dc.date.available2026-07-07T09:59:40Z
dc.descriptionRecognizing analogies, synonyms, antonyms, and associations appear to be four distinct tasks, requiring distinct NLP algorithms. In the past, the four tasks have been treated independently, using a wide variety of algorithms. These four semantic classes, however, are a tiny sample of the full range of semantic phenomena, and we cannot afford to create ad hoc algorithms for each semantic phenomenon; we need to seek a unified approach. We propose to subsume a broad range of phenomena under analogies. To limit the scope of this paper, we restrict our attention to the subsumption of synonyms, antonyms, and associations. We introduce a supervised corpus-based machine learning algorithm for classifying analogous word pairs, and we show that it can solve multiple-choice SAT analogy questions, TOEFL synonym questions, ESL synonym-antonym questions, and similar-associated-both questions from cognitive psychology.
dc.descriptionrelated work available at http://purl.org/peter.turney/
dc.identifierhttps://arxiv.org/abs/0809.0124
dc.identifierhttp://arxiv.org/abs/0809.0124
dc.identifierProceedings of the 22nd International Conference on Computational Linguistics (Coling 2008), August 2008, Manchester, UK, Pages 905-912
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/168108
dc.subjectComputation and Language
dc.subjectInformation Retrieval
dc.subjectMachine Learning
dc.subjectH.3.1; I.2.6; I.2.7
dc.titleA Uniform Approach to Analogies, Synonyms, Antonyms, and Associations
dc.typetext

Files

Collections

arXiv