Computer Science Colloquium, ChengXiang Zhai, Aug. 23

[Erna Amerman]

University of Illinois at Urbana-Champaign

Department of Computer Science

The Thomas M. Siebel Center for Computer Science
201 North Goodwin Avenue
Urbana, Illinois 61801-2302  USA


COMPUTER SCIENCE COLLOQUIUM
  (and Graduate Seminar)


   User-Centered Adaptive Information Retrieval


     ChengXiang Zhai
     Department of Computer Science
     University of Illinois at Urbana-Champaign

     August 23 (Wednesday), 2006 at 4:00 p.m.
     1404 Siebel Center for Computer Science
	
			
A major limitation of current search engines (e.g., Google) is that the 
retrieval decision is generally made based solely on the query and 
document collection; information about the actual user and the search 
context is largely ignored. This limitation makes the retrieval 
performance of existing search engines inherently non-optimal since 
different users (and the same user in different situations) may use 
exactly the same query to search for different information.

In this talk, I will present some recent work that aims to break this 
limitation and develop a new retrieval strategy called user-centered 
adaptive information retrieval (UCAIR). In UCAIR, the retrieval process 
is modeled generally as a sequential decision process, in which the 
system responds to each user action by choosing an optimal system 
action, and all the available user information and search context would 
be exploited to optimize each retrieval decision. I will present a 
decision-theoretic framework for optimal interactive information 
retrieval and show that such a decision-theoretic view of retrieval can 
naturally suggest many interesting ways to achieve personalization in an 
interactive search system. I will then discuss two specific lines of 
research toward personalized search. First, I will show how we can 
improve document ranking through implicit user modeling with statistical 
language models. Second, I will discuss some comparative and temporal 
text mining techniques that can be exploited to customize search results 
according to different task context of a user.


Bio:
ChengXiang Zhai is an Assistant Professor of Computer Science at the 
University of Illinois at Urbana-Champaign, where he also holds a joint 
appointment at the Institute for Genomic Biology and the Graduate School 
of Library and Information Science. He received a Ph.D. in Computer 
Science from Nanjing University in 1990, and a Ph.D. in Language and 
Information Technologies from Carnegie Mellon University in 2002. He 
worked at Clairvoyance Corp. as a Research Scientist and, later, a 
Senior Research Scientist from 1997 to 2000. His research interests 
include text information management, natural language processing, 
machine learning, and bioinformatics.
He was a program chair for ACM CIKM 2004 and is a program chair for 
NAACL HLT 2007. He has served on the program committee of most top 
conferences on information retrieval, natural language processing, data 
mining, and machine learning, and is an invited participant of the 
National Academy of Engineering's 12th annual Frontiers of Engineering 
Symposium. He has received the title ``UIUC Incomplete List of Teachers 
Ranked as Excellent'' in Spring 2005, an NSF CAREER Award in 2004, the 
ACM SIGIR 2004 Best Paper Award, and the 2004 Presidential Early Career 
Award for Scientists and Engineers (PECASE).


If you would like to subscribe to announcement:
http://mail.cs.uiuc.edu/mailman/listinfo/announce