A Simple Approach to Building Ensembles of Naive Bayesian Classifiers for Word Sense Disambiguation

摘要

This paper presents a corpus-based approach to word sense disambiguation thatbuilds an ensemble of Naive Bayesian classifiers, each of which is based onlexical features that represent co--occurring words in varying sized windows ofcontext. Despite the simplicity of this approach, empirical resultsdisambiguating the widely studied nouns line and interest show that such anensemble achieves accuracy rivaling the best previously published results.