Fine-Grained Word Sense Disambiguation Based on Parallel Corpora, Word Alignment, Word Clustering and Aligned Wordnets

Simple item page
dc.creatorTufis, Dan
dc.creatorIon, Radu
dc.creatorIde, Nancy
dc.date2005-03-10
dc.date.accessioned2026-07-07T03:22:43Z
dc.date.available2026-07-07T03:22:43Z
dc.descriptionThe paper presents a method for word sense disambiguation based on parallel corpora. The method exploits recent advances in word alignment and word clustering based on automatic extraction of translation equivalents and being supported by available aligned wordnets for the languages in the corpus. The wordnets are aligned to the Princeton Wordnet, according to the principles established by EuroWordNet. The evaluation of the WSD system, implementing the method described herein showed very encouraging results. The same system used in a validation mode, can be used to check and spot alignment errors in multilingually aligned wordnets as BalkaNet and EuroWordNet.
dc.description7 pages in Proc. of COLING2005
dc.identifierhttps://arxiv.org/abs/cs/0503024
dc.identifierhttp://arxiv.org/abs/cs/0503024
dc.identifierIn proceedings of the 20th International Conference on Computational Linguistics, COLING2004, Geneva, 2004, pp. 1312-1318
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/32660
dc.subjectArtificial Intelligence
dc.subjectComputation and Language
dc.titleFine-Grained Word Sense Disambiguation Based on Parallel Corpora, Word Alignment, Word Clustering and Aligned Wordnets
dc.typetext

Files

Collections

arXiv