CARE: Commonsense-Aware Emotional Response Generation with Latent Concepts
This work aims to improve the quality of emotional response generation for conversational AI by integrating commonsense, addressing a limitation in existing models that often neglect one aspect.
This paper addresses the problem of generating emotional responses in conversational AI that also incorporate rationality, specifically commonsense. The authors propose CARE, a model that learns and constructs commonsense-aware emotional latent concepts and integrates them into response generation, resulting in more accurate and commonsense-aware emotional responses and improved human ratings compared to state-of-the-art models.
Rationality and emotion are two fundamental elements of humans. Endowing agents with rationality and emotion has been one of the major milestones in AI. However, in the field of conversational AI, most existing models only specialize in one aspect and neglect the other, which often leads to dull or unrelated responses. In this paper, we hypothesize that combining rationality and emotion into conversational agents can improve response quality. To test the hypothesis, we focus on one fundamental aspect of rationality, i.e., commonsense, and propose CARE, a novel model for commonsense-aware emotional response generation. Specifically, we first propose a framework to learn and construct commonsense-aware emotional latent concepts of the response given an input message and a desired emotion. We then propose three methods to collaboratively incorporate the latent concepts into response generation. Experimental results on two large-scale datasets support our hypothesis and show that our model can produce more accurate and commonsense-aware emotional responses and achieve better human ratings than state-of-the-art models that only specialize in one aspect.