Forest-Based Neural Machine Translation
Forest-Based Neural Machine Translation
复制标题
DOI：
10.18653/v1/p18-1116
复制
发表时间：
2018-07
期刊：
影响因子：
--
通讯作者：
Chunpeng Ma;Akihiro Tamura;M. Utiyama;T. Zhao;E. Sumita
中科院分区：
文献类型：
--
作者：
Chunpeng Ma;Akihiro Tamura;M. Utiyama;T. Zhao;E. Sumita
基于树的神经机器翻译(NMT)方法虽然取得了令人印象深刻的性能，但存在一个重大缺陷：它们只使用1-Best句法树来指导翻译，这可能会由于句法错误而引入翻译错误。对于统计机器翻译(SMT)，基于森林的方法已经被证明是解决这个问题的有效方法，而对于NMT，这种方法还没有被尝试过。本文提出了一种基于森林的NMT方法，该方法在一个简单的序列到序列的框架下(即森林到序列的NMT模型)转换线性化的包装森林。该方法的BLEU得分高于基于序列到序列的自然机器翻译、基于树的自然机器翻译和基于森林的SMT系统。
Tree-based neural machine translation (NMT) approaches, although achieved impressive performance, suffer from a major drawback: they only use the 1-best parse tree to direct the translation, which potentially introduces translation mistakes due to parsing errors. For statistical machine translation (SMT), forest-based methods have been proven to be effective for solving this problem, while for NMT this kind of approach has not been attempted. This paper proposes a forest-based NMT method that translates a linearized packed forest under a simple sequence-to-sequence framework (i.e., a forest-to-sequence NMT model). The BLEU score of the proposed method is higher than that of the sequence-to-sequence NMT, tree-based NMT, and forest-based SMT systems.