Exemplars-guided Empathetic Response Generation Controlled by the Elements of Human Communication

TL;DR

This paper introduces an exemplars-guided approach for empathetic response generation that incorporates elements of human communication, improving response quality through retrieval and synthetic labels, beyond just emotion recognition.

Contribution

The paper proposes a novel method using exemplars and synthetic labels for elements of human communication to enhance empathetic response generation.

Findings

Significant improvement in automated empathy metrics.

Enhanced human-evaluated empathy quality.

Effective use of dense passage retrieval for exemplars.

Abstract

The majority of existing methods for empathetic response generation rely on the emotion of the context to generate empathetic responses. However, empathy is much more than generating responses with an appropriate emotion. It also often entails subtle expressions of understanding and personal resonance with the situation of the other interlocutor. Unfortunately, such qualities are difficult to quantify and the datasets lack the relevant annotations. To address this issue, in this paper we propose an approach that relies on exemplars to cue the generative model on fine stylistic properties that signal empathy to the interlocutor. To this end, we employ dense passage retrieval to extract relevant exemplary responses from the training set. Three elements of human communication -- emotional presence, interpretation, and exploration, and sentiment are additionally introduced using synthetic labels to guide the generation towards empathy. The human evaluation is also extended by these elements of human communication. We empirically show that these approaches yield significant improvements in empathetic response quality in terms of both automated and human-evaluated metrics. The implementation is available at https://github.com/declare-lab/exemplary-empathy.