International Workshop on Spoken Language Translation (IWSLT) 2007
Our statistical machine translation system that uses large Japanese-English parallel sentences and long phrase tables is described. We collected 698,973 Japanese-English parallel sentences, and we used long phrase tables. Also, we utilized general tools for statistical machine translation, such as Giza++, moses, and training-phrase-model.perl. We used these data and these tools. We challenge the contest for IWSLT07. In which task was the result (0.4321 BLEU) obtained.
Full Paper Presentation
Bibliographic reference. Murakami, Jin'ichi / Tokuhisa, Masato / Ikehara, Satoru (2007): "Statistical machine translation using large j/e parallel corpus and long phrase tables", In IWSLT-2007, 151-156.