More about HKUST
Responsive Information Architect: Context-Sensitive Information Seeking
Speaker: Dr. Michelle Zhou Research Manager IBM T. J. Watson Research Center Title: "Responsive Information Architect: Context-Sensitive Information Seeking" Date: Thursday, 3 February 2005 Time: 4:00pm - 5:00pm Venue: Room 3464 (Conference Room, via lift nos. 25/26) HKUST Abstract: Imagine the next generation of multimedia information portals, where users are able to obtain information through an intelligent multimodal interaction that is tailored to the tasks you are performing, customized to your personal preferences, and adapted to your context and interaction devices. To realize this vision, we are building an infrastructure, called Responsive Information Architect (RIA), which engages users in a dynamically generated multimodal, multimedia conversation to aid users in exploring large and complex information spaces. Unlike existing information access paradigm that forces users to explore information following pre-defined paths (e.g., GUI menus), RIA allows users to express their information requests flexibly using multiple modalities, such as GUI, natural language, and gesture. Using a rich context, such as conversation history and data semantics, RIA is capable of understanding user inputs, including complex data queries (e.g., "tell me about cities in the north along hudson river with at least 5000 people"), abbreviated requests (e.g., "what about golf courses"), and imprecise and ambiguous ones. To create tailored responses to such diverse user queries introduced during a conversation, we automate the generation of RIA responses. In particular, we use optimization-based approaches to select/organize desired content, and assign the proper media to convey different types of content. To present the intended content in a specific medium, we develop case-based learning algorithms to dynamically synthesis speech and visual presentations. As a result, RIA provides users with a customized multimedia presentation of retrieved information, including both speech and graphics. ******************* Biography: Michelle Zhou is a research manager at IBM T. J. Watson Research Center, where she manages the department of intelligent multimedia interaction. Her research interests include 3D multimedia user interfaces, intelligent multimodal conversation systems, context-based multimedia presentation authoring, and information visualization. Zhou received a Ph.D. in Computer Science from Columbia University in 1999. Her work on automated generation of interactive visual/multimedia explanations has been published in a wide variety of conferences and journals, including CHI, IJCAI/AAAI,ACM Multimedia, and IEEE Visualization/InfoVis. Her more recent work on automated generation of information graphics by examples has been featured both in IEEE Computer Magazine, and in the visualization frontier special issue at New York Academy of Sciences. Zhou is also active in research communities both inside and outside of IBM. She has chaired the multimedia professional impact community (MMPIC) at IBM for the past 2 years. She co-organized the international conference on Smart Graphics, and served as program committee members for top-rated conferences, including IEEE Visualization/InfoVis and ACM Multimedia.