Paper: Effective Phrase Translation Extraction From Alignment Models

ACL ID P03-1041
Title Effective Phrase Translation Extraction From Alignment Models
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2003

Phrase level translation models are ef- fective in improving translation qual- ity by addressing the problem of local re-ordering across language boundaries. Methods that attempt to fundamentally modify the traditional IBM translation model to incorporate phrases typically do so at a prohibitive computational cost. We present a technique that begins with im- proved IBM models to create phrase level knowledge sources that effectively repre- sent local as well as global phrasal con- text. Our method is robust to noisy align- ments at both the sentence and corpus level, delivering high quality phrase level translation pairs that contribute to signif- icant improvements in translation quality (as measured by the BLEU metric) over word based lexica as well as a competing alignment based method....