Exemplars-guided Empathetic Response Generation Controlled by the Elements of Human Communication
This work addresses the challenge of generating more nuanced empathetic responses in dialogue systems, which is important for improving human-computer interaction, though it is incremental as it builds on existing methods by adding new guidance mechanisms.
The paper tackles the problem of generating empathetic responses that go beyond just matching emotion by incorporating subtle qualities like understanding and personal resonance, which are difficult to quantify. It proposes an approach using exemplars and elements of human communication, showing significant improvements in empathetic response quality as measured by automated and human-evaluated metrics.
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.