Paper: Ensemble Methods For Unsupervised WSD

ACL ID P06-1013
Title Ensemble Methods For Unsupervised WSD
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2006

Combination methods are an effective way of improving system performance. This paper examines the bene ts of system combination for unsupervised WSD. We investigate several voting- and arbiter- based combination strategies over a di- verse pool of unsupervised WSD systems. Our combination methods rely on predom- inant senses which are derived automati- cally from raw text. Experiments using the SemCor and Senseval-3 data sets demon- strate that our ensembles yield signi - cantly better results when compared with state-of-the-art.