Don't Lose Yourself! Empathetic Response Generation via Explicit Self-Other Awareness

TL;DR

This paper introduces EmpSOA, a novel empathetic response generation model that explicitly incorporates self-other awareness through three stages, leading to more empathetic and human-like chatbot responses.

Contribution

It proposes a new framework with self-other differentiation, modulation, and generation stages to enhance empathy in chatbot responses, addressing limitations of prior methods.

Findings

EmpSOA outperforms baselines in automatic evaluations.

Human assessments confirm improved empathy in responses.

The model effectively maintains and regulates self-other awareness.

Abstract

As a critical step to achieve human-like chatbots, empathetic response generation has attained increasing interests. Previous attempts are incomplete and not sufficient enough to elicit empathy because they only focus on the initial aspect of empathy to automatically mimic the feelings and thoughts of the user via other-awareness. However, they ignore to maintain and take the own views of the system into account, which is a crucial process to achieve the empathy called self-other awareness. To this end, we propose to generate Empathetic response with explicit Self-Other Awareness (EmpSOA). Specifically, three stages, self-other differentiation, self-other modulation and self-other generation, are devised to clearly maintain, regulate and inject the self-other aware information into the process of empathetic response generation. Both automatic and human evaluations on the benchmark dataset demonstrate the superiority of EmpSOA to generate more empathetic responses.