Neural chat translation aims to translate bilingual conversational text,
which has a broad application in international exchanges and cooperation.
Despite the impressive performance of sentence-level and context-aware Neural
Machine Translation (NMT), there still remain challenges to translate bilingual
conversational text due to its inherent characteristics such as role
preference, dialogue coherence, and translation consistency. In this paper, we
aim to promote the translation quality of conversational text by modeling the
above properties. Specifically, we design three latent variational modules to
learn the distributions of bilingual conversational characteristics. Through
sampling from these learned distributions, the latent variables, tailored for
role preference, dialogue coherence, and translation consistency, are
incorporated into the NMT model for better translation. We evaluate our
approach on the benchmark dataset BConTrasT (English-German) and a
self-collected bilingual dialogue corpus, named BMELD (English-Chinese).
Extensive experiments show that our approach notably boosts the performance
over strong baselines by a large margin and significantly surpasses some
state-of-the-art context-aware NMT models in terms of BLEU and TER.
Additionally, we make the BMELD dataset publicly available for the research
community.

本研究旨在通过设计潜在变分模块来提高自然语言机器翻译中针对双语对话文本的翻译质量， 在英德数据集 BConTrasT 以及英汉数据集 BMELD 上的实验证明该方法较好地增强了翻译质量并明显超过了一些最先进的具有上下文感知的 NMT 模型，并且还公开了 BMELD 数据集供研究人员使用。