Paper: Using A Semantic Concordance For Sense Identification

ACL ID H94-1046
Title Using A Semantic Concordance For Sense Identification
Venue Human Language Technologies
Session Main Conference
Year 1994

This paper proposes benchmarks for systems of automatic sense identification. A textual corpus in which open-class words had been tagged both syntactically and semantically was used to explore three statistical strategies for sense identification: a guess- ing heuristic, a most-frequent heuristic, and a co-occurrence heuris- tic. When no information about sense-frequencies was available, the guessing heuristic using the numbers of alternative senses in WordNet was correct 45% of the time. When statistics for sense- frequancies were derived from a semantic concordance, the assumption that each word is used in its most frequently occurring sense was correct 69% of the time; when that figure was calculated for polysemous words alone, it dropped to 58%. And when a co- occur~nce heuristic took ...