%0 Conference Paper %B Proceedings of the Conference on Empirical Methods in Natural Language Processing %D 2008 %T Computing word-pair antonymy %A Mohammad,Saif %A Dorr, Bonnie J %A Hirst,Graeme %X Knowing the degree of antonymy between words has widespread applications in natural language processing. Manually-created lexicons have limited coverage and do not include most semantically contrasting word pairs. We present a new automatic and empirical measure of antonymy that combines corpus statistics with the structure of a published thesaurus. The approach is evaluated on a set of closest-opposite questions, obtaining a precision of over 80%. Along the way, we discuss what humans consider antonymous and how antonymy manifests itself in utterances. %B Proceedings of the Conference on Empirical Methods in Natural Language Processing %S EMNLP '08 %I Association for Computational Linguistics %C Stroudsburg, PA, USA %P 982 - 991 %8 2008/// %G eng %U http://dl.acm.org/citation.cfm?id=1613715.1613843