Minimum Bayes-Risk Alignment of Bilingual Texts

Download: slides.

Minimum Bayes-Risk Alignment of Bilingual Texts” by S. Kumar and W. Byrne. In Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing, (Philadelphia, PA, USA), 2002, pp. 140-147 (8 pages).

Abstract

We present Minimum Bayes-Risk word alignment for machine translation. This statistical, model-based approach attempts to minimize the expected risk of alignment errors under loss functions that measure alignment quality. We describe various loss functions, including some that incorporate linguistic analysis as can be obtained from parse trees, and show that these approaches can improve alignments of the English-French Hansards.

Download: slides.

BibTeX entry:

@inproceedings{minriskmtalign_emnlp02,
   author = {S. Kumar and W. Byrne},
   title = {Minimum {B}ayes-Risk Alignment of Bilingual Texts},
   booktitle = {Proceedings of the 2002 Conference on Empirical Methods in
	Natural Language Processing},
   pages = {140--147 (8 pages)},
   address = {Philadelphia, PA, USA},
   year = {2002},
   url = {http://www.aclweb.org/anthology/W/W02/W02-1019.pdf}
}

Back to Bill Byrne publications.