International Workshop on Spoken Language Translation (IWSLT) 2007 Trento, Italy October 15-16, 2007

Larger Feature Set Approach for Machine Translation in IWSLT 2007

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

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

The NTT Statistical Machine Translation System employs a large number of feature functions. First, k-best translation candidates are generated by an efficient decoding method of hierarchical phrase-based translation. Second, the k-best translations are reranked. In both steps, sparse binary features — of the order of millions — are integrated during the search. This paper gives the details of the two steps and shows the results for the Evaluation campaign of the International Workshop on Spoken Language Translation (IWSLT) 2007.

Full Paper     Presentation

Bibliographic reference.  Watanabe, Taro / Suzuki, Jun / Sudoh, Katsuhito / Tsukada, Hajime / Isozaki, Hideki (2007): "Larger feature set approach for machine translation in IWSLT 2007", In IWSLT-2007, 111-118.