International Workshop on Spoken Language Translation (IWSLT) 2004
Keihanna Science City, Kyoto, Japan
This system is an experiment of examples based approach. It is based on a corpus containing 220 thousand sentence pairs with word alignment. The system contains four parts: matching and search, fragment matching, fragment assembling, evaluation and post processing. We use word alignment information to find and combine fragments.
Full Paper Presentation
Bibliographic reference. Hou, Hongxu / Dang, Dan / Zou, Gang / Yu, Hongkui / Liu, Yang / Xiong, Deyi / Liu, Qun (2004): "An EBMT system based on word alignment", In IWSLT-2004, 47-49.