... Quirk. 2007. An iteratively-trained segmentation-free phrase translation model for statistical machine translation. In Proceedings ofthe 2nd Workshop on Statistical Machine Translation,pages 112–119.David ... Watanabe2, Eiichiro Sumita2, Shinsuke Mori1, Tatsuya Kawahara11Graduate School of Informatics, Kyoto UniversityYoshida Honmachi, Sakyo-ku, Kyoto, Japan2National Institute of Information ... phrase-based statistical machine translation (SMT) systems(Koehn et al., 2003) takes unaligned bilingual train-ing data as input, and outputs a scored table ofphrase pairs. This phrase table...