Semi-automatic Induction of Systematic Polysemy from WordNet.
Noriko Tomuro · 1998
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. 1 Introduction WordNet (Miller, 1990) has been used as a general resource of broad-coverage lexical information in many Natural Language Processing (NLP) tasks, including sense tagging, text summarizationand machine translation. However, like other large-scale knowledge-base systems or machine readable dictionaries (MRDs), WordNet contains massive ambiguity and redundancy. In particular, since WordNet senses are more fine-grained than most other MRDs such as LDOCE (Procter, 1978), each word entry is more amb...