The phenomenal success of web search engines such as Google is built on massive data redundancy, guiding users from simplistic queries to relevant information sources. For domains such as technical and scientific literature, however, this redundancy is severely limited, due to editorial controls on originality of content. Here there is a clear need to go beyond simple keyword search in order to service what are often complex information needs. In this talk I will present a frank and accessible account of text mining techniques developed to enhance information access, and abstract away from simple word sequences to syntactically and semantically richer representations of the information encoded in text.
Timothy Baldwin is a Senior Lecturer in the Department of Computer Science and Software Engineering, University of Melbourne. His research - funded by the ARC, NICTA, NTT, Google and others - encompasses computational and theoretical linguistics, text mining, text categorisation and information retrieval. He has given invited talks at various conferences, summer schools and universities worldwide, and is the author of over 100 journal and conference publications. He is currently on the editorial board of Computational Linguistics, a series editor for CSLI Publications, and a member of the Deep Linguistic Processing with HPSG Initiative (DELPH-IN).
Timothy Baldwin will be introduced by Kent Fitch,
Programmer, IT Division, National Library of Australia
Time: 12.30 to 13.30
Date: Friday 27 June 2008
Venue: National Library of Australia Theatre
This is a free event
Web Content Manager
Web Publishing Branch, IT Division
National Library of Australia
Thursday, June 26, 2008
Information access in technical and scientific literature
The National Library of Australia runs an excellent series of free Digital Culture talks. The next is "Information access in technical and scientific literature: search and you may possibly find", 12.30, Friday 27 June 2008 at the National Library of Australia Theatre, Canberra: