tailieunhanh - Báo cáo khoa học: "Bilingual Terminology Acquisition from Comparable Corpora and Phrasal Translation to Cross-Language Information Retrieval"

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. | Bilingual Terminology Acquisition from Comparable Corpora and Phrasal Translation to Cross-Language Information Retrieval Fatiha Sadat Masatoshi Yoshikawa Shunsuke Uemura Nara Institute of Science and Technology Nagoya University Nara Institute of Science and Technology Nara 630-0101 Japan Nagoya 464-8601 Japan Nara 630-0101 Japan fatia-s yosikawa uemurag@ Abstract 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 rescoring 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. 1 Introduction Although corpora have been an object of study of some decades recent years saw an increased interest in their use and construction. With this increased interest and awareness has come an expansion in the application to knowledge acquisition such as bilingual terminology. In addition non-aligned comparable corpora have been given a special interest in bilingual terminology acquisition and lexical resources enrichment Dejean et al. 2002 Fung 2000 Koehn and Knight 2o02 Rapp 1999 . This paper presents a novel approach to bilingual terminology acquisition and disambiguation from scarce resources such as comparable corpora phrasal translation through re-scoring techniques as well as evaluations on Cross-Language Information Retrieval CLIR . CLIR consists of retrieving documents written in one language using queries written in another language. An application is completed on a .