用预定义双语对增强神经机器翻译

Enhancing Neural Machine Translations with Pre-Defined Bilingual Pairs

将预先定义的双语对融入神经机器翻译(NMT)中一直是一项有较大应用场景,但具有挑战性的任务。受限于NMT的非离散特性以及逐词解码策略,想要在NMT中显式地融入外部双语对往往需要在解码期间修改集束搜索算法,或者对模型进行复杂修改。该文提出并探索了一种简单的将预先指定双语对融入NMT的方法,包括:(1)对训练数据进行适当的预处理,以添加有关预定义的双语信息;(2)使用部分共享的词向量以及额外向量增强信号,帮助模型区分预先指定的双语对和其他翻译文本。在多个语种上的实验和分析表明,该方法可以极大提高预定义短语被成功翻译的概率,达到接近99%(中英的基准是73.8%)的效果。

Integrating pre-defined bilingual pairs into Neural Machine Translation(NMT)has always been a challenging task with substantial application scenarios.Limited by the word-by-word decoding strategy,the explicit integration of external bilingual pairs into NMT often requires modifying the beam search decoding algorithm or even the model itself.This paper proposes a simple method of incorporating pre-defined bilingual pairs into NMT:(1)preprocessing the training data to add information about pre-defined bilingual pairs;(2)using partially shared embeddings help the model distinguish between pre-defined bilingual pairs and other texts.Experiments and analysis in multiple language pairs show that the method can improve the probability of successful translation of pre-defined bilingual pairs,reaching nearly 99%(the Chinese-English benchmark is 73.8%).