Paper: Unsupervised Word Sense Disambiguation Rivaling Supervised Methods

ACL ID P95-1026
Title Unsupervised Word Sense Disambiguation Rivaling Supervised Methods
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 1995
Authors

This paper presents an unsupervised learn- ing algorithm for sense disambiguation that, when trained on unannotated English text, rivals the performance of supervised techniques that require time-consuming hand annotations. The algorithm is based on two powerful constraints - that words tend to have one sense per discourse and one sense per collocation - exploited in an iterative bootstrapping procedure. Tested accuracy exceeds 96%.