A Weighted Finite State Transducer implementation of the alignment template model for statistical machine translation

Download: slides.

A Weighted Finite State Transducer implementation of the alignment template model for statistical machine translation” by S. Kumar and W. Byrne. In Proceedings of HLT-NAACL, 2003, pp. 63 -- 70 (8 pages).

Abstract

We present a derivation of the alignment template model for statistical machine translation and an implementation of the model using weighted finite state transducers. The approach we describe allows us to implement each constituent distribution of the model as a weighted finite state transducer or acceptor. We show that bitext word alignment and translation under the model can be performed with standard FSM operations involving these transducers. One of the benefits of using this framework is that it obviates the need to develop specialized search procedures, even for the generation of lattices or N-Best lists of bitext word alignments and translation hypotheses. We evaluate the implementation of the model on the Frenchto- English Hansards task and report alignment and translation performance.

Download: slides.

BibTeX entry:

@inproceedings{attm_hlt03,
   author = {S. Kumar and W. Byrne},
   title = {A Weighted Finite State Transducer implementation of the
	alignment template model for statistical machine translation},
   booktitle = {Proceedings of HLT-NAACL},
   pages = {63 -- 70 (8 pages)},
   year = {2003},
   url = {http://www.aclweb.org/anthology/N/N03/N03-1019.pdf}
}

Back to Bill Byrne publications.