Unsupervised Word Sense Disambiguation with Multilingual Representations

Erwin Fernandez-Ordoñez, Rada Mihalcea, Samer Hassan


Abstract
In 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.
Anthology ID:
L12-1646
Volume:
Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12)
Month:
May
Year:
2012
Address:
Istanbul, Turkey
Editors:
Nicoletta Calzolari, Khalid Choukri, Thierry Declerck, Mehmet Uğur Doğan, Bente Maegaard, Joseph Mariani, Asuncion Moreno, Jan Odijk, Stelios Piperidis
Venue:
LREC
SIG:
Publisher:
European Language Resources Association (ELRA)
Note:
Pages:
847–851
Language:
URL:
http://www.lrec-conf.org/proceedings/lrec2012/pdf/1082_Paper.pdf
DOI:
Bibkey:
Cite (ACL):
Erwin Fernandez-Ordoñez, Rada Mihalcea, and Samer Hassan. 2012. Unsupervised Word Sense Disambiguation with Multilingual Representations. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 847–851, Istanbul, Turkey. European Language Resources Association (ELRA).
Cite (Informal):
Unsupervised Word Sense Disambiguation with Multilingual Representations (Fernandez-Ordoñez et al., LREC 2012)
Copy Citation:
PDF:
http://www.lrec-conf.org/proceedings/lrec2012/pdf/1082_Paper.pdf