PECER: Empathetic Response Generation Via Dynamic Personality Extraction and Contextual Emotional Reasoning

Abstract

Empathy is a key factor in human emotional communication and social interaction. Personality is closely related to empathy, which is shaped by the interaction of cognition and affection, and plays a crucial role in emotional expression. However, previous studies have neglected personality as an important empathetic factor. In this work, we propose a dynamic Personality Extraction and Contextual Emotional Reasoning (PECER) model for empathetic dialogue generation. We constructed a contextual emotional reasoner that predicts emotional reactions based on dialogue history. Then we use a personality extractor to dynamically extract the speaker’s personality. Furthermore, a fusion mechanism is designed to inject dialogue history, personality and emotional reactions into the empathetic response generation process. Experimental results show that PECER outperforms state-of-the-art baselines in both automatic and human evaluation.