Efficient path counting transducers for minimum Bayes-risk decoding of statistical machine translation lattices (2010)
| Citations: | 3 - 3 self |
BibTeX
@MISC{Blackwood10efficientpath,
author = {Graeme Blackwood and Adrià De Gispert and William Byrne},
title = {Efficient path counting transducers for minimum Bayes-risk decoding of statistical machine translation lattices},
year = {2010}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
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. 1
Citations
| 179 | Improved backing-off for m-gram language modeling - Kneser, Ney - 1995 |
| 78 | Minimum Bayes-risk decoding for statistical machine translation - Kumar, Byrne - 2004 |
| 27 | HMM word and phrase alignment for statistical machine translation - Deng, Byrne - 2008 |
| 14 | Wojciech Skut, and Mehryar Mohri. 2007. OpenFst: A general and efficient weighted finite-state transducer library - Allauzen, Riley, et al. |
| 14 | 2009b. Hierarchical phrase-based translation with weighted finite state transducers - Iglesias, Gispert, et al. |
| 2 | An open-source, weighted finitestate transducer library and its applications to speech and language - OpenFST |
| 2 | English gigaword third edition - Graff, Kong, et al. - 2007 |
| 1 | Expected similarity maximization - Allauzen, Kumar, et al. - 2010 |
