Word Translation Disambiguation without Parallel Texts

Hits: 3952
Research areas: Year: 2011
Type of Publication: In Proceedings Keywords: word sense disambiguation, vector space models, n-gram language models
Authors:
  • 33, 39 29
Book title: Proceedings of the International Workshop on Using Linguistic Information for Hybrid Machine Translation
Address: Barcelona, Spain
Organization: LIHMT 2011 Month: November 18
ISBN: 9788461529957
Abstract:
Word Translation Disambiguation means to select the best translation(s) given a source word in context and a set of target candidates. Two approaches to determining similarity between input and sample context are presented, using n-gram and vector space models with huge annotated monolingual corpora as main knowledge source, rather than relying on large parallel corpora. Experiments on SemEval’s Cross-LingualWord Sense Disambiguation task (2010 English -German part) show some models on average surpassing the baselines, suggesting that translation disambiguation without parallel texts is feasible.
JRESEARCH_FULLTEXT: MarsiEtAl_WTD_2011.pdf