Enhancing the possibilities of corpus-based investigations: Word sense disambiguation on query results of large text corpora

摘要

Common large digital text corpora do not distinguish between different meanings of word forms, intense manual effort has to be done for disambiguation tasks when querying for homonyms or polysemes. To improve this situation, we ran experiments with automatic word sense disambiguation methods operating directly on the output of the corpus query. In this paper, we present experiments with topic models to cluster search result snippets in order to separate occurrences of homonymous or polysemous queried words by their meanings.