Towards human-like dialogue systems, current emotional dialogue approaches jointly model emotion and semantics with a unified neural network. This strategy tends to generate safe responses due to the mutual restriction between emotion and semantics, and requires rare emotion-annotated large-scale dialogue corpus. Inspired by the "think twice" behavior in human dialogue, we propose a two-stage conversational agent for the generation of emotional dialogue. Firstly, a dialogue model trained without the emotion-annotated dialogue corpus generates a prototype response that meets the contextual semantics. Secondly, the first-stage prototype is modified by a controllable emotion refiner with the empathy hypothesis. Experimental results on the DailyDialog and EmpatheticDialogues datasets demonstrate that the proposed conversational outperforms the comparison models in emotion generation and maintains the semantic performance in automatic and human evaluations.

翻译：为实现类人对话系统，当前的情感对话方法通常采用统一的神经网络联合建模情感与语义。由于情感与语义之间的相互制约，该策略倾向于生成安全回应，且需要稀缺的带情感标注的大规模对话语料。受人类对话中“三思而后言”行为启发，我们提出一种用于情感对话生成的两阶段对话代理。首先，未经情感标注对话语料训练的对话模型生成符合上下文语义的原型响应；其次，第一阶段的原型响应由具有共情假设的可控情感优化器进行修正。在DailyDialog和EmpatheticDialogues数据集上的实验结果表明，所提出的对话代理在自动评估与人工评估中，其情感生成效果优于对比模型，同时保持了语义性能。