Efficient Path Counting Transducers for Minimum Bayes-Risk Decoding of Statistical Machine Translation Lattices

Download: Poster.

Efficient Path Counting Transducers for Minimum Bayes-Risk Decoding of Statistical Machine Translation Lattices” by G. Blackwood, A. de Gispert, and W. Byrne. In Proceedings of the Annual Meeting of the Association for Computational Linguistics -- Short Papers, 2010, pp. 27-32 (6 pages).

Abstract

This paper presents an efficient implementation of linearised lattice minimum Bayes-risk decoding using weighted finite state transducers. We introduce transducers to efficiently count lattice paths containing n-grams and use these to gather the required statistics. We show that these procedures can be implemented exactly through simple transformations of word sequences to sequences of n-grams. This yields a novel implementation of lattice minimum Bayes-risk decoding which is fast and exact even for very large lattices.

Download: Poster.

BibTeX entry:

@inproceedings{pathcountacl2010,
   author = {G. Blackwood and A. de Gispert and W. Byrne},
   title = {Efficient Path Counting Transducers for Minimum {B}ayes-Risk
	Decoding of Statistical Machine Translation Lattices},
   booktitle = {Proceedings of the Annual Meeting of the Association for
	Computational Linguistics -- Short Papers},
   pages = {27--32 (6 pages)},
   year = {2010},
   url = {http://www.aclweb.org/anthology/P/P10/P10-2006.pdf}
}

Back to Bill Byrne publications.