EmpHi: Generating Empathetic Responses with Human-like Intents
This addresses the issue of limited empathetic intents in conversational AI for applications like mental health support, though it is incremental as it builds on existing empathetic dialogue methods.
The paper tackled the problem of monotonous empathy in empathetic conversations by proposing EmpHi, a model that generates responses with human-like empathetic intents, resulting in outperforming state-of-the-art models in empathy, relevance, and diversity on evaluations.
In empathetic conversations, humans express their empathy to others with empathetic intents. However, most existing empathetic conversational methods suffer from a lack of empathetic intents, which leads to monotonous empathy. To address the bias of the empathetic intents distribution between empathetic dialogue models and humans, we propose a novel model to generate empathetic responses with human-consistent empathetic intents, EmpHi for short. Precisely, EmpHi learns the distribution of potential empathetic intents with a discrete latent variable, then combines both implicit and explicit intent representation to generate responses with various empathetic intents. Experiments show that EmpHi outperforms state-of-the-art models in terms of empathy, relevance, and diversity on both automatic and human evaluation. Moreover, the case studies demonstrate the high interpretability and outstanding performance of our model.