Lexically Cohesive Neural Machine Translation with Copy Mechanism
Lexically Cohesive Neural Machine Translation with Copy Mechanism
复制标题
DOI：
--
复制
发表时间：
2020-10
期刊：
影响因子：
--
通讯作者：
V. Mishra;Chenhui Chu;Yuki Arase
中科院分区：
文献类型：
--
作者：
V. Mishra;Chenhui Chu;Yuki Arase
词汇衔接翻译在文档级翻译中保持了词汇选择的一致性。我们将复制机制应用到上下文感知神经机器翻译模型中，以允许从以前的翻译输出中复制单词。与以往的上下文感知神经机器翻译模型，处理所有的话语现象隐式不同，我们的模型显式地解决词汇衔接问题，提高输出单词的概率一致。我们使用语篇翻译评估数据集进行了日英翻译实验。实验结果表明，与以往的上下文感知模型相比，该模型显著提高了词汇衔接能力。
Lexically cohesive translations preserve consistency in word choices in document-level translation. We employ a copy mechanism into a context-aware neural machine translation model to allow copying words from previous translation outputs. Different from previous context-aware neural machine translation models that handle all the discourse phenomena implicitly, our model explicitly addresses the lexical cohesion problem by boosting the probabilities to output words consistently. We conduct experiments on Japanese to English translation using an evaluation dataset for discourse translation. The results showed that the proposed model significantly improved lexical cohesion compared to previous context-aware models.