Local Phrase Reordering Models for Statistical Machine Translation

Download: slides.

Local Phrase Reordering Models for Statistical Machine Translation” by S. Kumar and W. Byrne. In Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, 2005, pp. 161-168 (8 pages).

Abstract

We describe stochastic models of local phrase movement that can be incorporated into a Statistical Machine Translation (SMT) system. These models provide properly formulated, non-deficient, probability distributions over reordered phrase sequences. They are implemented by Weighted Finite State Transducers. We describe EM-style parameter re-estimation procedures based on phrase alignment under the complete translation model incorporating reordering. Our experiments show that the reordering model yields substantial improvements in translation performance on Arabic-to-English and Chinese-to-English MT tasks. We also show that the procedure scales as the bitext size is increased.

Download: slides.

BibTeX entry:

@inproceedings{hlt05:smtporder,
   author = {S. Kumar and W. Byrne},
   title = {Local Phrase Reordering Models for Statistical Machine
	Translation},
   booktitle = {Proceedings of Human Language Technology Conference and
	Conference on Empirical Methods in Natural Language Processing},
   pages = {161--168 (8 pages)},
   year = {2005},
   url = {http://www.aclweb.org/anthology/H/H05/H05-1021.pdf}
}

Back to Bill Byrne publications.