Paper: HMM Word And Phrase Alignment For Statistical Machine Translation

ACL ID H05-1022
Title HMM Word And Phrase Alignment For Statistical Machine Translation
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2005
Authors
  • Yonggang Deng (Johns Hopkins University, Baltimore MD)
  • William Byrne (Johns Hopkins University, Baltimore MD; Cambridge University, Cambridge UK)

HMM-based models are developed for the alignment of words and phrases in bitext. The models are formulated so that align- ment and parameter estimation can be per- formed efficiently. We find that Chinese- English word alignment performance is comparable to that of IBM Model-4 even over large training bitexts. Phrase pairs extracted from word alignments generated under the model can also be used for phrase-based translation, and in Chinese to English and Arabic to English transla- tion, performance is comparable to sys- tems based on Model-4 alignments. Di- rect phrase pair induction under the model is described and shown to improve trans- lation performance.