StyEmp: Stylizing Empathetic Response Generation via Multi-Grained Prefix Encoder and Personality Reinforcement

TL;DR

StyEmp is a novel approach for empathetic response generation that incorporates a multi-grained prefix encoder and personality reinforcement to produce responses that are both empathetic and consistent with a specified personality.

Contribution

It introduces a multi-grained prefix encoder and a contrastive learning-based personality reinforcement module for stylized empathetic response generation.

Findings

Outperforms baselines in empathy and personality consistency

Effective in capturing complex personality-empathy relationships

Validated on EMPATHETICDIALOGUES benchmark

Abstract

Recent approaches for empathetic response generation mainly focus on emotional resonance and user understanding, without considering the system's personality. Consistent personality is evident in real human expression and is important for creating trustworthy systems. To address this problem, we propose StyEmp, which aims to stylize the empathetic response generation with a consistent personality. Specifically, it incorporates a multi-grained prefix mechanism designed to capture the intricate relationship between a system's personality and its empathetic expressions. Furthermore, we introduce a personality reinforcement module that leverages contrastive learning to calibrate the generation model, ensuring that responses are both empathetic and reflective of a distinct personality. Automatic and human evaluations on the EMPATHETICDIALOGUES benchmark show that StyEmp outperforms competitive baselines in terms of both empathy and personality expressions.