International Workshop on Spoken Language Translation (IWSLT) 2008 Honolulu, Hawaii, USA October 20-21, 2008

NTT Statistical Machine Translation System for IWSLT 2008

Katsuhito Sudoh, Taro Watanabe, Jun Suzuki, Hajime Tsukada, Hideki Isozaki

NTT Communication Science Laboratories, Seika-cho, Soraku-gun, Kyoto, Japan

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.

Full Paper     Presentation (pdf)

Bibliographic reference.  Sudoh, Katsuhito / Watanabe, Taro / Suzuki, Jun / Tsukada, Hajime / Isozaki, Hideki (2008): "NTT statistical machine translation system for IWSLT 2008", In IWSLT-2008, 92-97.