The present paper will seek to present an approach to bilingual lexicon extraction from non-aligned comparable corpora, phrasal translation as well as evaluations on Cross-Language Information Retrieval. A two-stages translation model is proposed for the acquisition of bilingual terminology from comparable corpora, disambiguation and selection of best translation alternatives according to their linguistics-based knowledge. Different re-scoring techniques are proposed and evaluated in order to select best phrasal translation alternatives. Results demonstrate that the proposed translation model yields better translations and retrieval effectiveness could be achieved across Japanese-English language pair.
展开▼
