Abstract
Word sense disambiguation has been recognized as a major problem in natural language processing research for over forty years. Both quantitive and qualitative methods have been tried, but much of this work has been stymied by difficulties in acquiring appropriate lexical resources. The availability of this testing and training material has enabled us to develop quantitative disambiguation methods that achieve 92% accuracy in discriminating between two very distinct senses of a noun. In the training phase, we collect a number of instances of each sense of the polysemous noun. Then in the testing phase, we are given a new instance of the noun, and are asked to assign the instance to one of the senses. We attempt to answer this question by comparing the context of the unknown instance with contexts of known instances using a Bayesian argument that has been applied successfully in related tasks such as author identification and information retrieval. The proposed method is probably most appropriate for those aspects of sense disambiguation that are closest to the information retrieval task. In particular, the proposed method was designed to disambiguate senses that are usually associated with different topics.
Similar content being viewed by others
References
Bar-Hillel. “Automatic Translation of Languages.” In Advances in Computers. Ed. Donald Booth and R. E. Meagher. New York: Academic Press, 1960.
Black, Ezra. Towards Computational Discrimination of English Word Senses. Ph.D. thesis. City University of New York, 1987.
Black, Ezra. “An Experiment in Computational Discrimination of English Word Senses.” IBM Journal of Research and Development, 32 (1988) 185–94.
Brown, Peter, Stephen Della Pietra, Vincent Della Pietra, and Robert Mercer. “Word Sense Disambiguation Using Statistical Methods.” In Proceedings of the 29th Annual Meeting of the Association for Computational Linguistics, 1991, 264–70.
Brown, Peter, Jennifer Lai, and Robert Mercer. “Aligning Sentences in Parallel Corpora.” In Proceedings of the 29th Annual Meeting of the Association for Computational Linguistics, 1991, 169–76.
Choueka, Yaacov, and Serge Lusignan. “Disambiguation by Short Contexts.” Computers and the Humanities, 19 (1985) 147–58.
Church, Kenneth. “A Stochastic Parts Program an Noun Phrase Parser for Unrestricted Text.” In Proceedings, IEEE International Conference on Acoustics, Speech and Signal Processing, Glasgow, 1989.
Cruse, D. A. Lexical Semantics. Cambridge: Cambridge University Press, 1986.
Dagan, Ido, Alon Itai, and Ulrike Schwall. “Two Languages are more Informative than One.” In Proceedings of the 29th Annual Meeting of the Association for Computational Linguistics, 1991, 130–37.
Fillmore, Charles, and Sue Atkins. “Word Meaning: Starting where MRD's Stop.” Invited paper given at the 29th Annual Meeting of the Association for Computational Linguistics, 1991.
Granger, Richard. “FOUL-UP A Program that Figures out Meanings of Words from Context.” IJCAII-77 (1977) 172–78.
Hearst, Marti. “Toward Noun Homonym Disambiguation Using Local Context in Large Text Corpora.” In Proceedings of the Seventh Annual Conference of the UW Centre for the New OED and Text Research. Waterloo, Ontario, Canada: UW Centre for the New OED and Text Research, University of Waterloo, 1991.
Hirschman, Lynette. “Discovering Sublanguage Discovery.” In Analyzing Language in Restricted Domains. Ed. Ralph Grishman and Richard Kittredge. Hillsdale, New Jersey: Lawrence Erlbaum, 1986.
Hirst, G. Semantic Interpretation and the Resolution of Ambiguity. Cambridge: Cambridge University Press, 1987.
Ide, N. M., and J. Veronis. “Very Large Neural Networks for Word Sense Disambiguation.” In Proceedings of the 9th European Conference on Artificial Intelligence, ECAI 90. Stockholm, 1990, pp. 366–68.
Isabelle, P. “Machine Translation at the TAUM Group.” In Machine Translation Today: The State of the Art. Ed. King, M. Edinburgh: Edinburgh University Press, 1984.
Jackson, Howard. Words and their Meaning, London: Longman, 1988.
Jacobs, Paul, George Krupka, Susan McRoy, Lisa Rau, Norman Sondheimer, and Uri Zernik. “Generic Text Processing: A Progress Report.” In Proceedings DARPA Speech and Natural Language Workshop, 1990, 359–64.
Jorgensen, Julia. “The Psychological Reality of Word Senses.” Journal of Psycholinguistic Research, 19, (1990) 167–90.
Kaplan, Abraham. “An Experimental Study of Ambiguity in Context.” Cited in Mechanical Translation, 1, 1–3 (1950).
Kay, M., and M. Rösenschein, M. “Text-Translation Alignment.” Computational Linguistics. (To appear.)
Kelly, Edward, and Phillip Stone. Computer Recognition of English Word Senses. Amsterdam: North-Holland, 1975.
Kucera, H., and W. Francis. Computational Analysis of Present-day American English. Providence: Brown University Press, 1967.
Lesk, Michael. “Automatic Sense Disambiguation: How to tell a Pine Cone from an Ice Cream Cone.” In Proceeding of the 1986 SIGDOC Conference. New York: Association for Computing Machinery, 1986.
Longman Group Ltd. Longman Dictionary of Contemporary English, Burnt Mill, England: Longman, 1978.
Masterson, Margaret. “Mechanical Pidgin Translation.” In Machine Translation. Ed. Donald Booth. New York: Wiley, 1967.
Mosteller, Fredrick, and David Wallace. Inference and Disputed Authorship: The Federalist. Reading, MA: Addison-Wesley, 1964.
Quine, W. v. O. Word and Object. Cambridge: MIT Press, 1960.
Reiger, Charles. “Viewing Parsing as Word Sense Discrimination.” In A Survey of Linguistic Science. Ed. W. Dingall. Greylock, 1977.
Sinclair, J., Hanks, P., Fox, G., Moon, R., Stock, P. et al.Collins Cobuild English Language Dictionary. London and Glasgow: Collins, 1987.
Small, S. and C. Rieger. “Parsing and Comprehending with Word Experts (A Theory and its Realization).” In Strategies for Natural Language Processing Ed. W. Lehnert and M. Ringle. Hillsdale, New Jersey: Lawrence Erlbaum, 1982.
Stone, Phillip, D. C. Dunphy, M. S. Smith, and D. M. Ogilvie. The General Inquirer: A Computer Approach to Content Analysis. Cambridge: MIT Press, 1966.
Walker, Donald. “Knowledge Resource Tools for Accessing Large Text Files.” In Machine Translation: Theoretical and Methodological Issues. Ed. Sergei Nirenbe. Cambridge, England: Cambridge University Press, 1987.
Weinreich, U. On Semantics. Philadelphia: University of Pennsylvania Press, 1979.
Weiss, Stephen. “Learning to Disambiguate.” Information Storage and Retrieval, 9 (1973), 33–41.
Yngve, Victor. “Syntax and the Problem of Multiple Meaning.” In Machine Translation of Languages. Ed. William Locke and Donald Booth. New York: Wiley, 1955.
Zernik, Uri. “Tagging Word Senses in Corpus: The Needle in the Haystack Revisited.” In Text Based Intelligent Systems: Current Research in Text Analysis, Information Extraction, and Retrival. Ed. P. Jacobs. Schenectedy: GE Research and Development Center, 1990. 1990, 25–29.
Author information
Authors and Affiliations
Additional information
William Gale is in a statistics department at AT&T Bell Laboratories. He has done research in physics, radio astronomy, and economics in the past, and founded the Society for Artificial Intelligence and Statistics. His current interests include lexical issues such as word sense discrimination, word similarity measures, and word correspondences in parallel texts.
Kenneth Ward Church received his Ph.D. in Computer Science from MIT, and then went to work at AT&T Bell Laboratories on problems in speech and language. Recently, he has been advocating the use of statistical methods for analyzing large corpora.
David Yarowsky is currently pursuing a Ph.D. in Computer Science at the University of Pennsylvania. He spent several years at AT&T Bell Laboratories doing research in statistical natural language processing.
Rights and permissions
About this article
Cite this article
Gale, W.A., Church, K.W. & Yarowsky, D. A method for disambiguating word senses in a large corpus. Comput Hum 26, 415–439 (1992). https://doi.org/10.1007/BF00136984
Issue Date:
DOI: https://doi.org/10.1007/BF00136984