Coral: An Approach for Conversational Agents in Mental Health Applications

TL;DR

Coral is a generative empathetic chatbot designed for mental health support, utilizing large-scale pre-training and empathetic data to produce contextually appropriate, empathetic responses in open-domain conversations.

Contribution

The paper introduces a novel approach combining large-scale pre-training and empathetic data to enhance empathetic response generation in mental health conversational agents.

Findings

Achieved state-of-the-art results on Empathetic Dialogues test set.

Effectively maintains context in multi-turn conversations.

Produces more empathetic responses compared to previous models.

Abstract

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.