Unsupervised Word Sense Disambiguation with Multilingual Representations
13369Authors
nan
Abstract
AbstractIn this paper we investigate the role of multilingual features in improving word sense disambiguation. In particular, we explore the use of semantic clues derived from context translation to enrich the intended sense and therefore reduce ambiguity. Our experiments demonstrate up to 26% increase in disambiguation accuracy by utilizing multilingual features as compared to the monolingual baseline.
Keywords
Full Content
nan
Labeled Text
AbstractIn this paper we investigate the role of multilingual features in improving word sense disambiguation. In particular, we explore the use of semantic clues derived from context translation to enrich the intended sense and therefore reduce ambiguity. Our experiments demonstrate up to 26% increase in disambiguation accuracy by utilizing multilingual features as compared to the monolingual baseline.
Publication Details
- Paper ID:
- 13369
- Year:
- 2012
- Publication:
- TIPSTER
- Publication Type:
- conf
- DOI:
- nan