Chunk-Based Statistical Translation

Taro Watanabe, Eiichiro Sumita, Hiroshi G. Okuno

Abstract: 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 broad-coverage Japanese-English traveling corpus and achieved improved performance.