CARE: Causality Reasoning for Empathetic Responses by Conditional Graph Generation

TL;DR

CARE introduces a novel causality reasoning framework for empathetic response generation, modeling interdependent causalities to improve dialogue understanding and response quality, achieving state-of-the-art results.

Contribution

The paper proposes the CVGAE model and multi-source attention mechanism to reason all plausible causalities simultaneously for empathetic conversations.

Findings

Achieves state-of-the-art performance on empathetic response benchmarks.

Effectively models interdependent causalities in dialogue.

Enhances response relevance and emotional understanding.

Abstract

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.