Coral: An Approach for Conversational Agents in Mental Health Applications
This addresses the problem of individuals who struggle to open up to human experts by providing an intermediate virtual step, though it appears incremental in improving empathy in chatbots.
The paper tackles the challenge of creating empathetic conversational agents for mental health by developing a generative open-domain chatbot that achieves state-of-the-art results on the Empathetic Dialogues test set.
It may be difficult for some individuals to open up and share their thoughts and feelings in front of a mental health expert. For those who are more at ease with a virtual agent, conversational agents can serve as an intermediate step in the right direction. The conversational agent must therefore be empathetic and able to conduct free-flowing conversations. To this effect, we present an approach for creating a generative empathetic open-domain chatbot that can be used for mental health applications. We leverage large scale pre-training and empathetic conversational data to make the responses more empathetic in nature and a multi-turn dialogue arrangement to maintain context. Our models achieve state-of-the-art results on the Empathetic Dialogues test set.