Abstract

Corpus-based sense disambiguation methods, like most other statistical NLP approaches, suffer from the problem of data sparseness. In this paper, we describe an approach which overcomes this problem using dictionary definitions. Using the definitionbased conceptual co-occurrence data collected from the relatively small Brown corpus, our sense disambignation system achieves an average accuracy comparable to human performance given the same contextual information.

Citations

627	Word association norms, mutual information, and lexicography - Church, Hanks - 1990
540	Class-based n-gram models of natural language - Brown, Pietra, et al. - 1992
477	Distributional clustering of English words - Pereira, Tishby, et al. - 1993
200	A method for disambiguating word senses in a large corpus. Computers and the Humanities - Gale, Church, et al. - 1992
166	Word sense disambiguation using statistical methods - Brown, Pietra, et al. - 1991
100	Two languages are more informative than one - Dagan, Itai, et al. - 1991
91	Transmission of Information - Fano - 1949
73	Contextual word similarity and estimation from sparse data - Dagan, Markus, et al. - 1993
65	Similarity-Based Estimation of Word Cooccurrence Probabilities - Dagan, Pereira, et al. - 1994
46	Wordnet and distributional analysis: A class-based approach to lexical discovery - Resnik - 1992
43	An experiment in computational discrimination of English word senses - Black - 1988
19	Smoothing of automatically generated selectional constraints - Grishman, Sterling - 1993
11	Do We Need Linguistics When We Have Statistics? A Comparative Analysis of the Contributions of Linguistic Cues to a Statistical Word Grouping System - Hatzivassiloglou - 1994