Empathetic Dialogue Generation via Sensitive Emotion Recognition and Sensible Knowledge Selection
This work improves empathetic dialogue generation for applications like psychological counseling, but it is incremental as it builds on existing methods by refining emotion and knowledge integration.
The authors tackled the problem of generating empathetic dialogue responses by addressing dynamic emotion changes and harmonizing commonsense knowledge with emotions, resulting in SEEK outperforming strong baselines in automatic and manual evaluations on the EmpatheticDialogues dataset.
Empathy, which is widely used in psychological counselling, is a key trait of everyday human conversations. Equipped with commonsense knowledge, current approaches to empathetic response generation focus on capturing implicit emotion within dialogue context, where the emotions are treated as a static variable throughout the conversations. However, emotions change dynamically between utterances, which makes previous works difficult to perceive the emotion flow and predict the correct emotion of the target response, leading to inappropriate response. Furthermore, simply importing commonsense knowledge without harmonization may trigger the conflicts between knowledge and emotion, which confuse the model to choose incorrect information to guide the generation process. To address the above problems, we propose a Serial Encoding and Emotion-Knowledge interaction (SEEK) method for empathetic dialogue generation. We use a fine-grained encoding strategy which is more sensitive to the emotion dynamics (emotion flow) in the conversations to predict the emotion-intent characteristic of response. Besides, we design a novel framework to model the interaction between knowledge and emotion to generate more sensible response. Extensive experiments on EmpatheticDialogues demonstrate that SEEK outperforms the strong baselines in both automatic and manual evaluations.