Phrase-based statistical machine translation with weighted finite state transducers

Download: PDF.

“Phrase-based statistical machine translation with weighted finite state transducers” by W. Byrne, IRTG Summer School in Computational Linguistics and Psycholinguistics, University of Edinburgh, UK. Sep. 2008. Invited tutorial.

Abstract

The Transducer Translation Model (TTM) for phrase-based statistical machine translation system follows a generative model of translation and is implemented by the composition of component models realized as Weighted Finite State Transducers via the OpenFst Toolkit. This 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. This presentation describes how the system was used for the NIST 2008 Arabic-English machine translation evaluation task and for the Spanish-English and French-English translation in the ACL 2008 Third Workshop on Statistical Machine Translation Shared Task. General issues in using WFSTs for such tasks will also be discussed.

Download: PDF.

BibTeX entry:

@misc{byrne08:ed_irtg_tut,
   author = {W. Byrne},
   title = {Phrase-based statistical machine translation with weighted
	finite state transducers},
   publisher = {IRTG Summer School in Computational Linguistics and
	Psycholinguistics, University of Edinburgh, UK},
   address = {University of Edinburgh, UK},
   month = sep,
   year = {2008},
   note = {Invited tutorial.}
}

Back to Bill Byrne publications.