Minimum Bayes risk combination of translation hypotheses from alternative morphological decompositions

Download: Poster.

Minimum Bayes risk combination of translation hypotheses from alternative morphological decompositions” by A. de Gispert, S. Virpioja, M. Kurimo, and W. Byrne. In Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Short Papers, 2009, pp. 73-76 (4 pages).

Abstract

We describe a simple strategy to achieve translation performance improvements by combining output from identical statistical machine translation systems trained on alternative morphological decompositions of the source language. Combination is done by means of Minimum Bayes Risk decoding over a shared Nbest list. When translating into English from two highly inflected languages such as Arbic and Finnish we obtain significant improvements over simply selecting the best morphological decomposition.

Download: Poster.

BibTeX entry:

@inproceedings{adria_morph_hlt09,
   author = {A. de Gispert and S. Virpioja and M. Kurimo and W. Byrne},
   title = {Minimum {B}ayes risk combination of translation hypotheses
	from alternative morphological decompositions},
   booktitle = {Proceedings of Human Language Technologies: The 2009
	Annual Conference of the North American Chapter of the Association
	for Computational Linguistics, Companion Volume: Short Papers},
   pages = {73--76 (4 pages)},
   year = {2009},
   url = {http://www.aclweb.org/anthology/N/N09/N09-2019.pdf}
}

Back to Bill Byrne publications.