Achieving empathy is a crucial step toward humanized dialogue systems. Current approaches for empathetic dialogue generation mainly perceive an emotional label to generate an empathetic response conditioned on it, which simply treat emotions independently, but ignore the intrinsic emotion correlation in dialogues, resulting in inaccurate emotion perception and unsuitable response generation. In this paper, we propose a novel emotion correlation enhanced empathetic dialogue generation framework, which comprehensively realizes emotion correlation learning, utilization, and supervising. Specifically, a multi-resolution emotion graph is devised to capture context-based emotion interactions from different resolutions, further modeling emotion correlation. Then we propose an emotion correlation enhanced decoder, with a novel correlation-aware aggregation and soft/hard strategy, respectively improving the emotion perception and response generation. Experimental results on the benchmark dataset demonstrate the superiority of our model in both empathetic perception and expression.

翻译：实现共情是迈向人性化对话系统的关键一步。当前共情对话生成方法主要通过感知情感标签来生成条件化的共情回复，但这类方法将情感独立对待，忽略了对话中固有的情感关联，导致情感感知不准确及回复生成不适当。本文提出了一种新颖的情感关联增强共情对话生成框架，全面实现了情感关联的学习、利用与监督。具体而言，我们设计了一种多分辨率情感图，从不同分辨率捕捉基于上下文的情感交互，进而建模情感关联。随后提出一种情感关联增强解码器，通过新颖的关联感知聚合与软/硬策略，分别提升情感感知与回复生成能力。在基准数据集上的实验结果表明，我们的模型在共情感知与表达方面均具有优越性。