Language Grounding in Situated Communication

Abstract

To enable language communication with physical agents, language grounding becomes important. In this talk, I will give a brief introduction to some on-going work in my lab examining two levels of grounding: semantic grounding and communication grounding. Semantic grounding connects language to the agent’s perception and action. Communication grounding enables communication partners to reach a common ground. I will discuss these topics and their key challenges in the context of interactive task learning where humans can teach robots new tasks through language communication and action demonstration.

Bio

Joyce Chai is a Professor in the Department of Electrical Engineering and Computer Science at the University of Michigan. Her research interests include natural language processing, situated dialogue agents, human-robot communication, and artificial intelligence. Her recent work focuses on grounded language processing to facilitate natural communication with robots and other artificial agents. She holds a Ph.D. in Computer Science from Duke University.