题目：Towards Next-Generation Search Engines 报告人：Dr. ChengXiang Zhai 时间：2008年7月8日（周二）上午9点 地点：蒙民伟楼109室 Abstract: With the rapid growth of online information, search engines are beco
ming more and more important in our daily lives. Although the current-generati
on search engines are very useful for overcoming information overload, they ar
e limited in many ways, such as lack of user modeling and inadequate support f
or digesting search results. In this talk, I will present two lines of recent
research work of the Text Information Management group at the University of Il
linois at Urbana-Champaign that aim at developing novel models and algorithms
to enable the next-generation search engines to break these limitations. In on
e line of the work, I will present a decision-theoretic framework and statisti
cal language models for personalized search and show that search accuracy can
be improved significantly through using a user's search history. In the other
line, I will present a general probabilistic topic model for contextual text m
ining and show that the model can be used to analyze search results in many in
teresting ways to reveal subtopics and their variations over various context s
uch as time and location.
ChengXiang Zhai is an Assistant Professor of Computer Science at the Universi
ty of Illinois at Urbana-Champaign, where he also holds a joint appointment at
the Institute for Genomic Biology, Statistics, and the Graduate School of Lib
rary and Information Science. He received a Ph.D. in Computer Science from Nan
jing 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 information retrieval, text mining, natural lan
guage processing, machine learning, and bioinformatics. He serves on the edito
rial boards of ACM Transactions on Information Systems and Information Retriev
al Journal , and is a program co-chair of ACM CIKM 2004 , NAACL HLT 2007, and
ACM SIGIR 2009. He received an NSF CAREER Award in 2004, the ACM SIGIR 2004 Be
st Paper Award, and the 2004 Presidential Early Career Award for Scientists an
d Engineers (PECASE) (nominated by NSF).
|
