Simultaneous Neural Machine Translation with Constituent Label Prediction
Simultaneous Neural Machine Translation with Constituent Label Prediction
复制标题
DOI：
--
复制
发表时间：
2021-10
期刊：
影响因子：
--
通讯作者：
Yasumasa Kano;Katsuhito Sudoh;Satoshi Nakamura
中科院分区：
文献类型：
--
作者：
Yasumasa Kano;Katsuhito Sudoh;Satoshi Nakamura
同声翻译是在说话者说完之前开始翻译的任务，因此决定何时开始翻译过程很重要。然而，对于英语和日语等具有不同词序的语言对来说，决定是阅读更多输入单词还是开始翻译是很困难的。受预重新排序概念的启发，我们使用增量成分标签预测预测的下一个成分的标签提出了几个简单的决策规则。在英日同声翻译实验中，所提出的方法在质量延迟权衡方面优于基线。
Simultaneous translation is a task in which translation begins before the speaker has finished speaking, so it is important to decide when to start the translation process. However, deciding whether to read more input words or start to translate is difficult for language pairs with different word orders such as English and Japanese. Motivated by the concept of pre-reordering, we propose a couple of simple decision rules using the label of the next constituent predicted by incremental constituent label prediction. In experiments on English-to-Japanese simultaneous translation, the proposed method outperformed baselines in the quality-latency trade-off.