Empathetic AI: Teaching Computers Empathy and Politeness

The Conversational AI System, powered by Natural Language Processing (NLP) and Machine Learning has been at the forefront of the Artificial Intelligence (AI) revolution during the last few years. With the tremendous advancement in technologies and the phenomenal rise in the widespread adoption of AI-powered smart devices and virtual assistants, more and more organizations are very rapidly moving towards a conversation-driven interface to better engage their customers. The current and future intelligent conversational agents aim at being capable of an open-domain dialogue in such a way that is personable, consistent, empathetic, and engaging.  

 

As an example scenario, customer care is a platform used by the companies to provide guidance, assistance and in building stable customer relations. For the growth of any company or application it is necessary for the customer care agents to be cordial and amicable to the customer. Thus along with handling queries, it is important for the agents to provide customer satisfaction by greeting, empathizing, appreciating feedback, apologizing at the right time, and thus build a strong relation with the customer. For social good applications, such as mental health counseling, it is important to understand the emotional states of the victims and counsel in a polite and friendly environment.  

 

The talk will cover some of our recent research that attempts to build state-of-the-art conversational agents by leveraging techniques on natural language understanding, deep learning and Large Language Models (LLMs).