Situated Language Processing Towards Interactive Task Learning

With the emergence of a new generation of cognitive robots, enabling situated communication and collaboration has become increasingly important. However, effective dialog with artificial agents is very challenging. Humans and robots have different levels of linguistic, world, and task knowledge. They also have mismatched capabilities in perceiving the shared environment and performing joint tasks. These obstacles make it difficult for humans and robots to establish a common ground, which is essential for language-based communication. To address these problems, it is important for robots to continuously acquire knowledge and learn about the environment, actions, and tasks from human partners. In this talk, I will explore interactive task learning through natural language instructions, particularly focusing on grounding verbs and their arguments to perception and action.
Joyce Chai is a Professor in the Department of Computer Science and Engineering at Michigan State University. She received a Ph.D. in Computer Science from Duke University in 1998. Prior to joining MSU in 2003, she was a Research Staff Member at IBM T. J. Watson Research Center. Her research interests include natural language processing, situated dialogue, human-robot communication, and artificial intelligence. Her recent work has focused on grounded language processing to facilitate situated communication with robots and other artificial agents. She served as Program Co-chair for the Special Interest Group in Dialogue and Discourse (SIGDIAL) in 2011, the ACM International Conference on Intelligent User Interfaces (IUI) in 2014, and the North America Chapter of ACL "“ Human Language Technology (NAACL-HLT) in 2015. She is currently serving on the editorial board of the journal of Computational Linguistics. She is a recipient of the National Science Foundation Career Award in 2004 and the Best Long Paper Award from the Annual Meeting of Association of Computational Linguistics (ACL) in 2010.