Paper: Exploiting Aggregate Properties Of Bilingual Dictionaries For Distinguishing Senses Of English Words And Inducing English Sense Clusters

ACL ID P04-3007
Title Exploiting Aggregate Properties Of Bilingual Dictionaries For Distinguishing Senses Of English Words And Inducing English Sense Clusters
Venue Annual Meeting of the Association of Computational Linguistics
Session System Demonstration
Year 2004
Authors

We propose a novel method for inducing monolingual semantic hierarchies and sense clusters from numerous foreign-language-to-English bilingual dictionaries. The method exploits patterns of non-transitivity in transla- tions across multiple languages. No complex or hierar- chical structure is assumed or used in the input dictio- naries: each is initially parsed into the “lowest common denominator” form, which is to say, a list of pairs of the form (foreign word, English word). We then propose a monolingual synonymy measure derived from this ag- gregate resource, which is used to derive multilingually- motivated sense hierarchies for monolingual English words, with potential applications in word sense classifi- cation, lexicography and statistical machine translation.