Chunk-Based Statistical Translation

This paper describes an alternative translation model based on a text chunk under the framework of statistical machine translation. The translation model suggested here first performs chunking. Then, each word in a chunk is translated. Finally, translated chunks are reordered. Under this scenario of translation modeling, we have experimented on a broadcoverage Japanese-English traveling corpus and achieved improved performance.

• Type: Conference
• Year: 2003
• Where: ACL
• Authors: Taro Watanabe, Eiichiro Sumita, Hiroshi G. Okuno
• Keywords: ACL 2003, ACL 2007, Alternative Translation Model, Statistical Machine Translation, Translation Model