Bidirectional Decoding for Statistical Machine Translation
Bidirectional Decoding for Statistical Machine Translation
复制标题
DOI：
10.3115/1072228.1072278
复制
发表时间：
2002-08
期刊：
影响因子：
--
通讯作者：
Taro Watanabe;E. Sumita
中科院分区：
文献类型：
--
作者：
Taro Watanabe;E. Sumita
本文描述了从右向左解码方法，该方法通过从右向左生成来翻译输入字符串。此外，还提出了双向解码方法，通过双向生成输出和合并两个方向的部分输出，可以同时利用从左到右和从右到左解码方法的优点。对日英翻译的实验结果表明，从右到左的翻译方式更适合英日翻译，而从左到右的翻译方式更适合日英翻译。还观察到双向方法更适合英日翻译。
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.