融合双向依存自注意力机制的神经机器翻译

针对神经机器翻译中资源稀缺的问题，提出了一种基于双向依存自注意力机制（Bi-Dependency）的依存句法知识融合方法。首先，利用外部解析器对源句子解析得到依存解析数据；然后，将依存解析数据转化为父词位置向量和子词权重矩阵；最后，将依存知识融合到Transformer编码器的多头注意力机制上。利用Bi-Dependency，翻译模型可以同时对父词到子词、子词到父词两个方向的依存信息进行关注。双向翻译的实验结果表明，与Transformer模型相比，在富资源情况下，所提方法在汉-泰翻译上的BLEU值分别提升了1.07和0.86，在汉-英翻译上的BLEU值分别提升了0.79和0.68；在低资源情况下，所提方法在汉-泰翻译上的BLEU值分别提升了0.51和1.06，在汉-英翻译上的BLEU值分别提升了1.04和0.40。可见Bi-Dependency为模型提供了更丰富的依存信息，能够有效提升翻译性能。

Neural machine translation integrating bidirectional-dependency self-attention mechanism

Aiming at the problem of resource scarcity in neural machine translation， a method for fusion of dependency syntactic knowledge based on a Bidirectional-Dependency self-attention mechanism （Bi-Dependency） was proposed. Firstly， an external parser was used to parse the source sentence to obtain dependency parsing data. Then， the dependency parsing data was transformed into the position vector of the parent word and the weight matrix of the child word. Finally， the dependency knowledge was integrated into the multi-head attention mechanism of the Transformer encoder. By using Bi-Dependency， the translation model was able to simultaneously pay attention to the dependency information in both directions： the parent word to the child word and the child word to the parent word. Experimental results of bi-directional translation show that compared with the Transformer model， in the case of rich resources， the proposed method has the BLEU （BiLingual Evaluation Understudy） value on Chinese-Thai translation improved by 1.07 and 0.86 respectively， and the BLEU value on Chinese-English translation improved by 0.79 and 0.68 respectively； in the case of low resources， the proposed model has the BLEU value increased by 0.51 and 1.06 respectively on Chinese-Thai translation， and the BLEU value increased by 1.04 and 0.40 respectively on Chinese-English translation. It can be seen that Bi-Dependency provides the model with richer dependence information， which can effectively improve the translation performance.