In this paper, we present a novel distortion model for phrase-based statistical machine translation. Unlike the previous phrase distortion models whose role is to simply penalize nonmonotonic alignments[1, 2], the new model assigns the probability of relative position between two source language phrases aligned to the two adjacent target language phrases. The phrase translation probabilities and phrase distortion probabilities are calculated from the N-best phrase alignment of the training bilingual sentences. To obtain Nbest phrase alignment, we devised a novel phrase alignment algorithm based on word translation probabilities and N-best search. Experiments show that the phrase distortion model and phrase translation model improve the BLEU and NIST scores over the baseline method.
Cite as: Ohashi, K., Yamamoto, K., Saito, K., Nagata, M. (2005) NUT-NTT statistical machine translation system for IWSLT 2005. Proc. International Workshop on Spoken Language Translation (IWSLT 2005), 118-123
@inproceedings{ohashi05_iwslt,
author={Kazuteru Ohashi and Kazuhide Yamamoto and Kuniko Saito and Masaaki Nagata},
title={{NUT-NTT statistical machine translation system for IWSLT 2005}},
year=2005,
booktitle={Proc. International Workshop on Spoken Language Translation (IWSLT 2005)},
pages={118--123}
}