| Resumen |
Empathy is fundamental to humans among other animals. It is key to strengthening social cohesion, the cornerstone of health and success of societies. Thus, empathy could be an important component of effective human-computer interactions through conversations. This has motivated a whole sub-field of research focused on empathetic response generation. 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 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. © 2013 IEEE. |
