A Weighted Finite State Transducer Translation Template Model for Statistical Machine Translation

Download: PDF, see also CLSP Tech. Rep. 48, 2004.

“A Weighted Finite State Transducer Translation Template Model for Statistical Machine Translation” by S. Kumar, Y. Deng, and W. Byrne. Journal of Natural Language Engineering, vol. 12, no. 1, Mar. 2006, pp. 35-75 (41 pages).

Abstract

We present a Weighted Finite State Transducer Translation Template Model for statistical machine translation. 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 avoids 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 report and analyze bitext word alignment and translation performance of the model on French-English and Chinese-English tasks.

Download: PDF, see also CLSP Tech. Rep. 48, 2004.

BibTeX entry:

@article{kumar04:_weigh_finit_state_trans_trans,
   author = {S. Kumar and Y. Deng and W. Byrne},
   title = {A Weighted Finite State Transducer Translation Template Model
	for Statistical Machine Translation},
   journal = {Journal of Natural Language Engineering},
   volume = {12},
   number = {1},
   pages = {35--75 (41 pages)},
   month = mar,
   year = {2006}
}

Back to Bill Byrne publications.