This paper reports the NTT statistical translation system participating in the evaluation campaign of IWSLT 2005. The NTT system is based on a phrase translation model and utilizes a large number of features with a log-linear model. We studied the various features recently developed in this research field and evaluate the system using supplied data as well as publicly available Chinese, Japanese, and English data. Despite domain mismatch, additional data helped improve translation accuracy.
Cite as: Tsukada, H., Watanabe, T., Suzuki, J., Kazawa, H., Isozaki, H. (2005) The NTT statistical machine translation system for IWSLT2005. Proc. International Workshop on Spoken Language Translation (IWSLT 2005), 112-117
@inproceedings{tsukada05_iwslt,
author={Hajime Tsukada and Taro Watanabe and Jun Suzuki and Hideto Kazawa and Hideki Isozaki},
title={{The NTT statistical machine translation system for IWSLT2005}},
year=2005,
booktitle={Proc. International Workshop on Spoken Language Translation (IWSLT 2005)},
pages={112--117}
}