This paper describes the NAIST statistical machine translation system for the IWSLT2012 Evaluation Campaign. We participated in all TED Talk tasks, for a total of 11 languagepairs. For all tasks, we use the Moses phrase-based decoder and its experiment management system as a common base for building translation systems. The focus of our work is on performing a comprehensive comparison of a multitude of existing techniques for the TED task, exploring issues such as out-of-domain data filtering, minimum Bayes risk decoding, MERT vs. PRO tuning, word alignment combination, and morphology.
Cite as: Neubig, G., Duh, K., Ogushi, M., Kano, T., Kiso, T., Sakti, S., Toda, T., Nakamura, S. (2012) The NAIST machine translation system for IWSLT2012. Proc. International Workshop on Spoken Language Translation (IWSLT 2012), 54-60
@inproceedings{neubig12_iwslt,
author={Graham Neubig and Kevin Duh and Masaya Ogushi and Takatomo Kano and Tetsuo Kiso and Sakriani Sakti and Tomoki Toda and Satoshi Nakamura},
title={{The NAIST machine translation system for IWSLT2012}},
year=2012,
booktitle={Proc. International Workshop on Spoken Language Translation (IWSLT 2012)},
pages={54--60}
}