论文标题
护理：通过有条件图生成的促进反应的因果关系推理
CARE: Causality Reasoning for Empathetic Responses by Conditional Graph Generation
论文作者
论文摘要
善解人意反应产生的最新方法结合了情感因果关系，以增强对用户的感受和经历的理解。但是，这些方法遇到了两个关键问题。首先，他们仅考虑用户的情绪与用户的体验之间的因果关系，而忽略用户体验之间的因果关系。其次，他们忽略了因果关系之间的相互依存，并独立推理他们。为了解决上述问题，我们希望在用户的情感，对话历史和未来的对话内容中，同时且同时同时置换所有合理的因果关系。然后，我们将这些因果关系注入促进反应的反应产生中。具体而言，我们为因果关系推理设计了一个新模型，即条件变分图自动编码器（CVGAE），并在因果性输注的解码器中采用多源注意机制。我们将整个框架称为护理，缩写是为了善解人意的对话。实验结果表明我们的方法实现了最先进的性能。
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.
