Semi-automatic Induction of Systematic Polysemy from WordNet

Author: Noriko Tomuro
Journal-ref: In Proceedings of the workshop on Usage of WordNet in Natural Language Processing Systems at the 17th International Conference on Computational Linguistics (COLING '98) and the 36th Annual Meeting of the Association for Computational Linguistics (ACL'98)

Abstract

This paper describes a semi-automatic method of inducing underspecified semantic classes from WordNet verbs and nouns. An underspecified semantic class is an abstract semantic class which encodes systematic polysemy: a set of word senses that are related in systematic and predictable ways. We show the usefulness of the induced classes in the semantic interpretations and contextual inferences of real-word texts by applying them to the predicate-argument structures in Brown corpus.

Paper: Full paper (postscript 178k)