|
R. C. Moore, W. Yih, A. Bode
Improved Discriminative Bilingual Word Alignment
COLING-ACL-06
For many years, statistical machine translation relied on generative models to provide bilingual word alignments. In 2005, several independent efforts showed that discriminative models could be used to enhance or replace the standard generative approach. Building on this work, we demonstrate substantial improvement in word-alignment accuracy, partly though improved training methods, but predominantly through selection of more and better features. Our best model produces the lowest alignment error rate yet reported on Canadian Hansards bilingual data. @InProceedings{moore-yih-bode:2006:COLACL,
author = {Moore, Robert C. and Yih, Wen-tau and Bode, Andreas},
title = {Improved Discriminative Bilingual Word Alignment},
booktitle = {Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics},
month = {July},
year = {2006},
address = {Sydney, Australia},
publisher = {Association for Computational Linguistics},
pages = {513--520},
url = {http://www.aclweb.org/anthology/P/P06/P06-1065}
}
|
