Large-scale Statistical Machine Translation with Weighted Finite State Transducers

Download: PDF.

“Large-scale Statistical Machine Translation with Weighted Finite State Transducers” by G. Blackwood, A. de Gispert, J. Brunning, and W. Byrne. In Proceedings of FSMNLP 2008: Finite-State Methods and Natural Language Processing, (Ispra, Lago Maggiore, Italy), Sep. 2008.

Abstract

The Cambridge University Engineering Department phrase-based statistical machine translation system follows a generative model of translation and is implemented by the composition of component models 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 participation in the NIST 2008 Arabic-English machine translation evaluation task.

Download: PDF.

BibTeX entry:

@inproceedings{fsmnlp08:wfstmt,
   author = {G. Blackwood and A. de Gispert and J. Brunning and W. Byrne},
   title = {Large-scale Statistical Machine Translation with Weighted
	Finite State Transducers},
   booktitle = {Proceedings of FSMNLP 2008: Finite-State Methods and
	Natural Language Processing},
   pages = {(12 pages)},
   address = {Ispra, Lago Maggiore, Italy},
   month = sep,
   year = {2008}
}

Back to Bill Byrne publications.