Collloquium: Introduction to the CMU ArticuLab

The ArticuLab’s mission is to study human interaction in social and cultural contexts as the input into computational systems that in turn help us to better understand human interaction, and to improve and support human capabilities in areas that really matter. At the ArticuLab, we study how people communicate with and through technology. We use technology as a way of better studying human-human communication, and use the study of human-human communication to design better technology. This interest leads us to questions concerning the intersection of language, learning, the body, and computational systems, through a range of interdisciplinary methods and tools. Benefiting from the synergy of rigorous experimental methods and extensive computational modeling, our work contributes to theoretical research in cognitive science, communication studies, learning sciences, artificial intelligence, human-computer interaction, and many other related disciplines.

 

Michael Madaio

Ph.D. Student

Human Computer Interaction Institute

"'Yeah, I Think That’s Right': Understanding the Role of Hedged Feedback in Peer Tutoring Discourse"

 

Michael will discuss how the ArticuLab uses methods from computational linguistics and machine learning to understand the role of sociolinguistic phenomena in education. This talk will focus on the role that indirectness, or hedging, plays in the provision of feedback between collaborating learners, and how we integrate this hedged feedback into one particular educational technology, a “virtual peer tutor”.

 

Dr. Timo Baumann, Ph.D. 

Systems Scientist 

Language Technologies Institute

"Incremental Processing Makes for More Attentive Virtual Agents”

 

Human speakers and listeners process spoken language incrementally, piece-by-piece, and just-in-time, with the different processes involved working concurrently, on different time scales, and with varying degrees of specificity and flexibility. Typical language processing systems, in contrast, use a non-incremental pipeline architecture which can be an obstacle in interactive use-cases, where the future context is only partially known. He will present the IU approach towards incremental processing in general and, focusing on incremental speech output in particular, he describes an experiment in which speaking socially while waiting for content to be ready improves not only the perceived attentiveness of the agent but also improves measures of task success.