MIME: MIMicking Emotions for Empathetic Response Generation

TL;DR

This paper introduces MIME, a novel method for empathetic response generation that considers emotion polarity and mimicry, leading to more empathetic and contextually relevant responses with greater emotional diversity.

Contribution

It proposes a new approach that models emotion polarity and mimicry, improving empathy and relevance in responses over previous methods.

Findings

Enhanced empathy and relevance demonstrated through automatic and human evaluations.

Emotion polarity-based clustering improves response quality.

Increased emotional diversity in generated responses.

Abstract

Current approaches to empathetic response generation view the set of emotions expressed in the input text as a flat structure, where all the emotions are treated uniformly. We argue that empathetic responses often mimic the emotion of the user to a varying degree, depending on its positivity or negativity and content. We show that the consideration of this polarity-based emotion clusters and emotional mimicry results in improved empathy and contextual relevance of the response as compared to the state-of-the-art. Also, we introduce stochasticity into the emotion mixture that yields emotionally more varied empathetic responses than the previous work. We demonstrate the importance of these factors to empathetic response generation using both automatic- and human-based evaluations. The implementation of MIME is publicly available at https://github.com/declare-lab/MIME.