Discriminating Among Word Meanings by Identifying Similar Contexts

Word sense discrimination is an unsupervised clustering problem, which seeks to discover which instances of a word/s are used in the same meaning. This is done strictly based on information found in raw corpora, without using any sense tagged text or other existing knowledge sources. Our particular focus is to systematically compare the efficacy of a range of lexical features, context representations, and clustering algorithms when applied to this problem.