|
|
The web is revolutionizing information access, however current techniques for access to information on the web provide much room for improvement. Search engines do not provide comprehensive and up-to-date indices, and much of the scientific information on the web is poorly organized. This talk covers the current state of the accessibility and distribution of information on the web, and describes recent research on improved methods and intelligent agents for searching the web. The Inquirus metasearch engine and the CiteSeer scientific literature project are described. Inquirus improves web search by considering the information need of the user for source selection, query modification, and document ordering. Analyzing the current contents of documents allows Inquirus to do consistent ranking across sources, and ensures that results always reflect the current state of the web. CiteSeer is a digital library of scientific literature incorporating Autonomous Citation Indexing, user profiling, citation graph analysis, citation context extraction, related document identification, full-text indexing, and query-sensitive summaries. Autonomous Citation Indexing (ACI) autonomously creates citation indices of scientific literature. Compared to traditional citation indices, ACI can provide advantages in terms of cost, availability, comprehensiveness, efficiency, and timeliness. Joint work with Kurt Bollacker, Eric Glover, Lee Giles.
|
|
Steve Lawrence graduated summa cum laude from the Queensland University of Technology, Australia, with highest honors in both B.Sc. and B.Eng. degrees. His awards include an NEC Research Institute excellence award, a QUT university medal and award for excellence, ATERB and APRA priority scholarships, QEC and Telecom Australia Engineering prizes, and three prizes in successive years of the Australian Mathematics Competition. Dr. Lawrence received his PhD from the University of Queensland, Australia. Dr. Lawrence has authored or co-authored over 40 publications in areas including information retrieval, Web search, machine learning, citation indexing, face recognition, speech phoneme recognition, financial prediction, local approximation, generalization, local minima, and natural language grammatical inference. In addition to professional service including peer reviews for the NSF and several publications, Dr. Lawrence has been involved with the Computer Policy Committee, served as a postgraduate representative, and instigated the Neural Networks Discussion Group at the University of Queensland. Dr. Lawrence has been interviewed by over 30 news organizations including the New York Times, Wall Street Journal, Washington Post, Reuters, Associated Press, UPI, CNN, BBC, MSNBC, and NPR. Hundreds of articles about his research have appeared worldwide in over 10 languages.
