Syntax has been proven to be remarkably effective in neural machine translation (NMT). Previous models obtained syntax information from syntactic parsing tools and integrated it into NMT models to improve translation performance. In this work, we propose a method to incorporate syntax information into a complex-valued Encoder-Decoder architecture. The proposed model jointly learns word-level and syntax-level attention scores from the source side to the target side using an attention mechanism. Importantly, it is not dependent on specific network architectures and can be directly integrated into any existing sequence-to-sequence (Seq2Seq) framework. The experimental results demonstrate that the proposed method can bring significant improvements in BLEU scores on two datasets. In particular, the proposed method achieves a greater improvement in BLEU scores in translation tasks involving language pairs with significant syntactic differences.

翻译：句法已被证明在神经机器翻译（NMT）中具有显著效果。此前模型通过句法解析工具获取句法信息，并将其整合到NMT模型中以提高翻译性能。本文提出一种将句法信息融入复数值编码器-解码器架构的方法。该模型通过注意力机制，从源语言侧到目标语言侧联合学习词级和句法级注意力权重。重要的是，该方法不依赖于特定网络架构，可直接集成到任意现有的序列到序列（Seq2Seq）框架中。实验结果表明，所提方法能在两个数据集上显著提升BLEU分数。特别是，在涉及句法差异显著的语言对的翻译任务中，该方法在BLEU分数上的提升更为明显。