NTT statistical machine translation for IWSLT 2006.
Taro Watanabe, Jun Suzuki, Hajime Tsukada, Hideki Isozaki · 2006
We present the NTT translation system that is experimented for the evaluation campaign of “International Workshop on Spoken Language Translation (IWSLT). ” The system con-sists of two primary components: a hierarchical phrase-based statistical machine translation system and a reranking sys-tem. The former is conceptualized as a synchronous-CFG in which phrases are hierarchically combined using non-terminals. The latter uses a modified voted perceptron ap-proach with large number of features. Experiments showed that our hierarchical phrase-based model outperformed a conventional phrase-based model. In addition, our reranking algorithm further boosted the performance. 1.