Language Learning through Social and Embodied Experience

Joyce Chai

University of Michigan

The NLP Reading Group is excited to host Joyce Chai who will be giving a talk in-person on “Language Learning through Social and Embodied Experience”.

Talk Description

Human language learning is shaped by social and embodied experience. Through interaction with others, we acquire the meanings and uses of language from communicative context. Language learning is also grounded to our sensorimotor experiences with the physical world, which connects words to actions and perceptions. In this talk, I will present several studies in my lab that explore social and embodied context for grounded language learning in computational models. I will describe acquisition of grounded verb semantics through a notion of physical causality. I will show how corrective feedback accelerates language learning. I will further highlight the role of grounding in fast mapping and discuss the emergence of symbol grounding in LLMs.

Speaker Bio

Joyce Chai is a Professor in the Department of Electrical Engineering and Computer Science at the University of Michigan. She holds a Ph.D. in Computer Science from Duke University. Her research interests span from natural language processing and embodied AI to human-robot collaboration. Her current work explores the intersection between language, vision, and robotics to enable situated communication with embodied agents. She served on the executive board of NAACL and as Program Co-Chair for multiple conferences, most recently ACL 2020. She is a recipient of the NSF Career Award. She also received multiple awards with her students (e.g., Best Long Paper Award at ACL 2010, Outstanding Paper Awards at EMNLP 2021 and ACL 2023, and First Place in the Amazon Alexa AI Simbot Challenge 2023). She is a Fellow of ACL.

Logistics

Date: November 14th
Time: 2:00PM
Location: H04 or via Google Meet (See email)