Bidirectional Decoding for Statistical Machine Translation

This paper describes the right-to-left decoding method, which translates an input string by generating in right-to-left direction. In addition, presented is the bidirectional decoding method, that can take both of the advantages of left-to-right and right-to-left decoding method by generating output in both ways and by merging hypothesized partial outputs of two directions. The experimental results on Japanese and English translation showed that the right-to-left was better for Englith-to-Japanese translation, while the left-to-right was suitable for Japanese-to-English translation. It was also observed that the bidirectional method was better for English-to-Japanese translation.