Improving Neural Machine Translation with Neural Syntactic Distance

Improving Neural Machine Translation with Neural Syntactic Distance
复制标题

DOI:
10.18653/v1/n19-1205
复制
发表时间:
2019-06
期刊:
--
影响因子:
--
通讯作者:
Chunpeng Ma;Akihiro Tamura;M. Utiyama;E. Sumita;T. Zhao
Chunpeng Ma;Akihiro Tamura;M. Utiyama;E. Sumita;T. Zhao
中科院分区:
其他
文献类型:
--
作者:
Chunpeng Ma;Akihiro Tamura;M. Utiyama;E. Sumita;T. Zhao

文献摘要

相似文献

句法信息的显式使用已被证明是有用的神经机器翻译(NMT)。然而,以前的方法要么求助于树结构的神经网络或长的线性化序列,这两种都是效率低下的。神经句法距离(NSD)使我们能够使用长度与句子中单词数量相同的序列来表示组成树。NSD已用于成分分析,但不用于机器翻译。我们提出了五个策略,以改善NMT与NSD。实验表明,使用NSD改进NMT并不是微不足道的;然而,所提出的策略被证明可以提高基线模型的翻译性能(+2.1(En-Ja),+1.3(Ja-En),+1.2(En-Ch)和+1.0(Ch-En)BLEU)。
The explicit use of syntactic information has been proved useful for neural machine translation (NMT). However, previous methods resort to either tree-structured neural networks or long linearized sequences, both of which are inefficient. Neural syntactic distance (NSD) enables us to represent a constituent tree using a sequence whose length is identical to the number of words in the sentence. NSD has been used for constituent parsing, but not in machine translation. We propose five strategies to improve NMT with NSD. Experiments show that it is not trivial to improve NMT with NSD; however, the proposed strategies are shown to improve translation performance of the baseline model (+2.1 (En–Ja), +1.3 (Ja–En), +1.2 (En–Ch), and +1.0 (Ch–En) BLEU).