The NTT Statistical Machine Translation System consists of two primary components: a statistical machine translation decoder and a reranker. The decoder generates kbest translation canditates using a hierarchical phrase-based translation based on synchronous context-free grammar. The decoder employs a linear feature combination among several real-valued scores on translation and language models. The reranker reorders the k-best translation candidates using Ranking SVMs with a large number of sparse features. This paper describes the two components and presents the results for the evaluation campaign of IWSLT 2008.
Cite as: Sudoh, K., Watanabe, T., Suzuki, J., Tsukada, H., Isozaki, H. (2008) NTT statistical machine translation system for IWSLT 2008. Proc. International Workshop on Spoken Language Translation (IWSLT 2008), 92-97
@inproceedings{sudoh08_iwslt,
author={Katsuhito Sudoh and Taro Watanabe and Jun Suzuki and Hajime Tsukada and Hideki Isozaki},
title={{NTT statistical machine translation system for IWSLT 2008}},
year=2008,
booktitle={Proc. International Workshop on Spoken Language Translation (IWSLT 2008)},
pages={92--97}
}