Integrating Cross-Lingually Relevant News Articles and Monolingual Web Documents in Bilingual Lexicon Acquisition

摘要

In the framework of bilingual lexicon acquisition from cross-lingually relevant news articles on the Web, it is relatively harder to reliably estimate bilingual term correspondences for low frequency terms. Considering such a situation, this paper proposes to complementarily use much larger monolingual Web documents collected by search engines, as a resource for reliably re-estimating bilingual term correspondences. We experimentally show that, using a sufficient number of monolingual Web documents, it is quite possible to have reliable estimate of bilingual term correspondences for those low frequency terms.