Neural chat translation (NCT) aims to translate a cross-lingual chat between speakers of different languages. Existing context-aware NMT models cannot achieve satisfactory performances due to the following inherent problems: 1) limited resources of annotated bilingual dialogues; 2) the neglect of modelling conversational properties; 3) training discrepancy between different stages. To address these issues, in this paper, we propose a multi-task multi-stage transitional (MMT) training framework, where an NCT model is trained using the bilingual chat translation dataset and additional monolingual dialogues. We elaborately design two auxiliary tasks, namely utterance discrimination and speaker discrimination, to introduce the modelling of dialogue coherence and speaker characteristic into the NCT model. The training process consists of three stages: 1) sentence-level pre-training on large-scale parallel corpus; 2) intermediate training with auxiliary tasks using additional monolingual dialogues; 3) context-aware fine-tuning with gradual transition. Particularly, the second stage serves as an intermediate phase that alleviates the training discrepancy between the pre-training and fine-tuning stages. Moreover, to make the stage transition smoother, we train the NCT model using a gradual transition strategy, i.e., gradually transiting from using monolingual to bilingual dialogues. Extensive experiments on two language pairs demonstrate the effectiveness and superiority of our proposed training framework.

翻译：神经聊天翻译（NCT）旨在实现不同语言使用者之间的跨语言对话翻译。现有上下文感知的神经机器翻译模型因以下固有问题难以取得满意效果：1）标注双语对话资源有限；2）忽视对话属性建模；3）不同阶段存在训练差异。针对这些问题，本文提出一种多任务多阶段过渡性（MMT）训练框架，利用双语聊天翻译数据集及额外单语对话训练NCT模型。我们精心设计了两个辅助任务——话语辨识与说话人辨识，将对话连贯性与说话人特征建模引入NCT模型。训练过程包含三个阶段：1）基于大规模平行语料的句子级预训练；2）利用额外单语对话通过辅助任务进行中间训练；3）渐进式过渡的上下文感知微调。其中，第二阶段作为中间阶段，缓解了预训练与微调阶段间的训练差异。此外，为平滑阶段过渡，我们采用渐进过渡策略训练NCT模型，即逐步从使用单语对话过渡到双语对话。在两个语言对上的大量实验证明了所提出训练框架的有效性与优越性。