CARE: Causality Reasoning for Empathetic Responses by Conditional Graph Generation
This work addresses the challenge of improving empathetic dialogue systems for human-computer interaction, representing an incremental advancement by refining causality modeling.
The paper tackles the problem of generating empathetic responses by addressing limitations in existing methods that ignore causalities between user experiences and treat causalities independently, proposing a framework called CARE that uses a Conditional Variational Graph Auto-Encoder for interdependent causality reasoning and achieves state-of-the-art performance.
Recent approaches to empathetic response generation incorporate emotion causalities to enhance comprehension of both the user's feelings and experiences. However, these approaches suffer from two critical issues. First, they only consider causalities between the user's emotion and the user's experiences, and ignore those between the user's experiences. Second, they neglect interdependence among causalities and reason them independently. To solve the above problems, we expect to reason all plausible causalities interdependently and simultaneously, given the user's emotion, dialogue history, and future dialogue content. Then, we infuse these causalities into response generation for empathetic responses. Specifically, we design a new model, i.e., the Conditional Variational Graph Auto-Encoder (CVGAE), for the causality reasoning, and adopt a multi-source attention mechanism in the decoder for the causality infusion. We name the whole framework as CARE, abbreviated for CAusality Reasoning for Empathetic conversation. Experimental results indicate that our method achieves state-of-the-art performance.