Empathy is a trait that naturally manifests in human conversation. Theoretically, the birth of empathetic responses results from conscious alignment and interaction between cognition and affection of empathy. However, existing works rely solely on a single affective aspect or model cognition and affection independently, limiting the empathetic capabilities of the generated responses. To this end, based on the commonsense cognition graph and emotional concept graph constructed involving commonsense and concept knowledge, we design a two-level strategy to align coarse-grained (between contextual cognition and contextual emotional state) and fine-grained (between each specific cognition and corresponding emotional reaction) Cognition and Affection for reSponding Empathetically (CASE). Extensive experiments demonstrate that CASE outperforms the state-of-the-art baselines on automatic and human evaluation. Our code will be released.
翻译:从理论上讲,同情反应的产生产生于认知和情感之间的自觉一致和互动。然而,现有的作品完全依赖于单一感官方面或模式认知和感情独立地独立地依赖单一感官方面或模式认知和感情,限制了所产生反应的同情能力。为此,我们根据共同感认知图形和情感概念图设计了两级战略,将粗食(背景认知和背景情感状态之间)和精细(每种特定认知和相应的情感反应之间)的认知和情感反应(CASE)结合起来,从而限制所产生反应的同情能力。 广泛的实验表明,CASE在自动和人文评估方面超越了最先进的基线。我们的代码将会被发布。