H

ICS 661, Advanced Artificial Intelligence

Visiting Scholar Talk

Speaker:
Professor Douglas W. Oard, University of Maryland
Title:
Beyond the Document: Information Access for Conversational Content
Time and Place:
Monday November 5, 2012, 3-4 p.m., Hamilton basement room 3-F
Abstract:
Modern search technology evolved as a way of shifting the locus of control over information dissemination away from creators and publishers and closer to the ultimate consumers of that content. Today, however, we are increasingly applying the same technology to what we might call "conversational content" - content that was originally created with interaction rather than dissemination as the principal goal. In this talk, I will describe some of the challenges and opportunities that present themselves when searching conversational content and when trying to make sense of what has been found. I'll draw on examples from four projects: one focused on improving access to oral history interviews, one focused on disentangling interleaved conversations in text chat, one focused on resolving the identity of people whose names are mentioned in a large collection of corporate email, and one focused on reconstructing the Apollo missions to the Moon. Although I will mention how we have sought to address each of those challenges, my main objective will be to use the four cases as examples of a broad class of search and sense-making problems that we are only now beginning to see as one grand challenge problem that may well drive the development of the next generation of search technology.
About the Speaker:
Douglas Oard is a Professor at the University of Maryland, College Park, with joint appointments in the College of Information Studies and the Institute for Advanced Computer Studies, where he currently serves as director of the Computational Linguistics and Information Processing lab. Dr. Oard earned his Ph.D. in Electrical Engineering from the University of Maryland. His research interests center around the use of emerging technologies to support information seeking by end users. Additional information is available at http://terpconnect.umd.edu/~oard/.

David N. Chin / Chin@Hawaii.Edu