Large-scale statistical machine translation with weighted finite state transducers (2009)
| Venue: | In Post Proceedings of the 7th International Workshop on Finite-State Methods and Natural Language Processing, FSMNLP 2008 |
| Citations: | 5 - 3 self |
BibTeX
@INPROCEEDINGS{Blackwood09large-scalestatistical,
author = {Graeme Blackwood and Adrià De Gispert and Jamie Brunning and William Byrne},
title = {Large-scale statistical machine translation with weighted finite state transducers},
booktitle = {In Post Proceedings of the 7th International Workshop on Finite-State Methods and Natural Language Processing, FSMNLP 2008},
year = {2009},
pages = {39--49},
publisher = {IOS Press}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
statistical machine translation system follows a generative model of translation and is implemented by the composition of component models of translation and movement realised as Weighted Finite State Transducers. Our flexible architecture requires no special purpose decoder and readily handles the large-scale natural language processing demands of state-of-the-art machine translation systems. In this paper we describe the CUED system’s participation in the NIST 2008 Arabic-English machine translation evaluation task. Key words: Statistical machine translation, weighted finite state transducers, large-scale natural language processing, finite state grammars. 1
