论文信息 - Statistical Discrimination of the Synonymy/Antonymy Relationship Between Words

Statistical Discrimination of the Synonymy/Antonymy Relationship Between Words

A basic hypothesis is stated about the contextual and co-occurrence properties of synonymous words. On the basis of this hypothesis, several statistics are derived for use in discriminating between pairs of words which are synonymous and pairs of words which are nonsynonymous. The discriminating power of these statistics is tested on a corpus consisting of titles of physics theses. The tests indicate that two of the derived statistics have relatively high discriminating power. The results are interpreted and the possibility of obtaining better discriminating power is discussed.

Peter A. W. Lewis | P. B. Baxendale | J. L. Bennett

[1] A. E. Maxwell,et al. Classification Procedures Based on Bayes's Formula , 1960 .

[2] Godfrey Dewey,et al. Relativ frequency of English speech sounds , 1923 .

[3] Frank B. Baker,et al. Information Retrieval Based upon Latent Class Analysis , 1962, JACM.

[4] H. Edmund Stiles,et al. The Association Factor in Information Retrieval , 1961, JACM.

[5] M. Lois Marckworth. Dissertations in physics : an indexed bibliogrphy of all doctoral theses accepted by American universities, 1861-1959 , 1961 .

[6] Lauren B. Doyle,et al. Semantic Road Maps for Literature Searchers , 1961, JACM.

[7] J. Spiegel,et al. STATISTICAL ASSOCIATION PROCEDURES FOR MESSAGE CONTENT ANALYSIS , 1963 .

[8] P. E. Jones,et al. LINEAR ASSOCIATIVE INFORMATION RETRIEVAL , 1962 .

[9] N. Feather. Dissertations in physics: An indexed bibliography of all doctoral theses accepted by American universities, 1861–1959: Compiled by M. L. Marckworth. Stanford University Press, 1961. xii + 803 pp., $17.50 , 1961 .