MIME: MIMicking Emotions for Empathetic Response Generation
This work addresses the need for more nuanced empathetic AI responses in conversational systems, though it is incremental in improving existing emotion modeling approaches.
The paper tackled the problem of generating empathetic responses by modeling emotional mimicry based on polarity, resulting in improved empathy and contextual relevance compared to state-of-the-art methods, with gains demonstrated through automatic and human evaluations.
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.