Imagine being able to obtain information, not through an assortment of independently predesigned web sites, but rather through anintelligent multimodal conversation that is tailored to the task you are performing, customized to your personal preferences, and adapted to your context and interaction devices. To realize this vision, we are building an integrated paradigm, called Responsive Information Architect (RIA), which aims to support a full-fledged multimodal, multimedia conversation.

In particular, RIA can engage users in a dynamically formulated multimodal, multimedia conversation to aid users in understanding and navigating large and complex information spaces. We use a combination of knowledge-based planning and machine learning approaches to dynamically determine the contents of the response, to select the media for encoding the contents, and to automatically compose coordinated multimedia streams with embedded interaction controls (verbal or visual).

Bio:
Michelle Zhou is a research staff member at IBM T. J. Watson Research Center, where she manages the department of intelligent multimedia interaction. She received a Ph.D. in Computer Science from Columbia University. Her research interests include 3D user interfaces, multimedia authoring, and information visualization. She also currently chairs the Multimedia PIC at IBM Research.