Paper: SenseLearner: Word Sense Disambiguation For All Words In Unrestricted Text

ACL ID P05-3014
Title SenseLearner: Word Sense Disambiguation For All Words In Unrestricted Text
Venue Annual Meeting of the Association of Computational Linguistics
Session System Demonstration
Year 2005
Authors

This paper describes SENSELEARNER – a minimally supervised word sense disam- biguation system that attempts to disam- biguate all content words in a text using WordNet senses. We evaluate the accu- racy of SENSELEARNER on several stan- dard sense-annotated data sets, and show that it compares favorably with the best re- sults reported during the recent SENSEVAL evaluations.