International Workshop on Spoken Language Translation (IWSLT) 2007
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.