Effect of Cross-Language IR in Bilingual Lexicon Acquisition from Comparable Corpora

Takehito Utsuro

Within the framework of translation knowledge acquisition from WWW news sites, we study issues on the effect of cross-language retrieval of relevant texts in bilingual lexicon acquisition from comparable corpora. We experimentally show that, by incoporating CLIR techniques, the number of candidate bilingual term pairs can be drastically reduced, where most of the discarded candidate pairs are not correct translation of each other.