Paper: A Phrase-Based Joint Probability Model For Statistical Machine Translation

ACL ID W02-1018
Title A Phrase-Based Joint Probability Model For Statistical Machine Translation
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2002
Authors

We present a joint probability model for statistical machine translation, which au- tomatically learns word and phrase equiv- alents from bilingual corpora. Transla- tions produced with parameters estimated using the joint model are more accu- rate than translations produced using IBM Model 4. 1 Motivation Most of the noisy-channel-based models used in statistical machine translation (MT) (Brown et al. , 1993) are conditional probability models. In the noisy-channel framework, each source sentence e in a parallel corpus is assumed to “generate” a target sentence f by means of a stochastic process, whose parameters are estimated using traditional EM tech- niques (Dempster et al. , 1977). The generative model explains how source words are mapped into target words and how target words are...