BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:The ILIAD Project: Language Technology Meets Linux Troubleshooting
  - Timothy Baldwin - University of Melbourne.
DTSTART:20070702T100000Z
DTEND:20070702T110000Z
UID:TALK7648@talks.cam.ac.uk
CONTACT:NLIP Seminars
DESCRIPTION:While web search engines such are remarkably successful at loc
 ating individual\ndocuments/sites typifying a given information type\, the
 y are largely unable to\ntrack data streams spanning multiple documents as
  found\, e.g.\, in mailing list\narchives. Additionally\, typical web sear
 ch engines have no facility to specify\nthe time span of documents to sear
 ch over\, and have only limited means of\npicking up on lexical variants o
 n a given query\, such that the exact wording\nof the query can be crucial
  to arriving at the desired document.\n\nIn the ILIAD (Improved Linux Info
 rmation Access by Data Mining) project we \naim to detect the underlying i
 nformation structure of a multi-document \ntext discourse\, which we then 
 distill into a factoid-based summary\, \nfiltering out any subjective info
 rmation content in the process. Our aim \nis to apply our technology to Li
 nux user web forums for improved \ninformation delivery.\n
LOCATION:SW01 Computer Laboratory
END:VEVENT
END:VCALENDAR