Neural machine translation (NMT) has shown great success as a new alternative to the traditional Statistical Machine Translation model in multiple languages. Early NMT models are based on sequence-to-sequence learning that encodes a sequence of source words into a vector space and generates another sequence of target words from the vector. In those NMT models, sentences are simply treated as sequences of words without any internal structure. In this article, we focus on the role of the syntactic structure of source sentences and propose a novel end-to-end syntactic NMT model, which we call a tree-to-sequence NMT model, extending a sequence-to-sequence model with the source-side phrase structure. Our proposed model has an attention mechanism that enables the decoder to generate a translated word while softly aligning it with phrases as well as words of the source sentence. We have empirically compared the proposed model with sequence-to-sequence models in various settings on Chinese-to-Japanese and English-to-Japanese translation tasks. Our experimental results suggest that the use of syntactic structure can be beneficial when the training data set is small, but is not as effective as using a bi-directional encoder. As the size of training data set increases, the benefits of using a syntactic tree tends to diminish.

中文翻译：

---

将源侧短语结构纳入神经机器翻译

神经机器翻译 (NMT) 作为多种语言中传统统计机器翻译模型的新替代方案，已取得巨大成功。早期的 NMT 模型基于序列到序列学习，将源词序列编码到向量空间中，并从向量生成另一个目标词序列。在那些 NMT 模型中，句子被简单地视为没有任何内部结构的单词序列。在本文中，我们关注源句句法结构的作用，并提出了一种新的端到端句法 NMT 模型，我们称之为树到序列 NMT 模型，扩展了序列到序列模型源端短语结构。我们提出的模型具有注意力机制，使解码器能够生成翻译的单词，同时将其与短语以及源句子的单词轻柔地对齐。我们根据经验将所提出的模型与各种设置中的序列到序列模型进行了比较，以处理中文到日文和英文到日文的翻译任务。我们的实验结果表明，当训练数据集较小时，使用句法结构可能是有益的，但不如使用双向编码器有效。随着训练数据集大小的增加，使用句法树的好处往往会减少。我们的实验结果表明，当训练数据集较小时，使用句法结构可能是有益的，但不如使用双向编码器有效。随着训练数据集大小的增加，使用句法树的好处往往会减少。我们的实验结果表明，当训练数据集较小时，使用句法结构可能是有益的，但不如使用双向编码器有效。随着训练数据集大小的增加，使用句法树的好处往往会减少。