Use of a Taxonomy of Empathetic Response Intents to Control and Interpret Empathy in Neural Chatbots

TL;DR

This paper introduces a taxonomy-based approach for controlling and interpreting empathy in neural chatbots, enabling more diverse and appropriate empathetic responses through a two-module system.

Contribution

It presents a novel framework using a taxonomy of empathetic response intents to improve the controllability and interpretability of empathetic responses in chatbots.

Findings

Taxonomy improves response diversity and appropriateness

Rule-based and neural models outperform end-to-end approaches

Human evaluation confirms enhanced empathetic response quality

Abstract

A recent trend in the domain of open-domain conversational agents is enabling them to converse empathetically to emotional prompts. Current approaches either follow an end-to-end approach or condition the responses on similar emotion labels to generate empathetic responses. But empathy is a broad concept that refers to the cognitive and emotional reactions of an individual to the observed experiences of another and it is more complex than mere mimicry of emotion. Hence, it requires identifying complex human conversational strategies and dynamics in addition to generic emotions to control and interpret empathetic responding capabilities of chatbots. In this work, we make use of a taxonomy of eight empathetic response intents in addition to generic emotion categories in building a dialogue response generation model capable of generating empathetic responses in a controllable and interpretable manner. It consists of two modules: 1) a response emotion/intent prediction module; and 2) a response generation module. We propose several rule-based and neural approaches to predict the next response's emotion/intent and generate responses conditioned on these predicted emotions/intents. Automatic and human evaluation results emphasize the importance of the use of the taxonomy of empathetic response intents in producing more diverse and empathetically more appropriate responses than end-to-end models.