论文标题
带有副本机制的词汇凝聚力神经机器翻译
Lexically Cohesive Neural Machine Translation with Copy Mechanism
论文作者
论文摘要
词汇凝聚的翻译在文档级翻译中保留单词选择中的一致性。我们将复制机制用于上下文感知的神经机器翻译模型，以允许复制以前的翻译输出中的单词。与以前的上下文感知的神经机器翻译模型不同，该模型隐含地处理所有话语现象，我们的模型通过提高概率始终如一地输出单词来明确解决词汇内聚力问题。我们使用评估数据集进行讲话翻译的日语对英文翻译进行实验。结果表明，与以前的上下文感知模型相比，提出的模型显着改善了词汇内聚力。
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.
