BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:NLP Reading group - Template-Based Information Extraction without 
 the Templates - Saad Aloteibi (University of Cambridge)
DTSTART:20110609T110000Z
DTEND:20110609T120000Z
UID:TALK31511@talks.cam.ac.uk
CONTACT:Jimme Jardine
DESCRIPTION:"Template-Based Information Extraction without the Templates".
  By Nathanael Chambers and Dan Jurafsky\n\nAbstract:\n\n"Standard algorith
 ms for template-based information extraction (IE) require predefined templ
 ate schemas\, and often labeled data\, to learn to extract their slot fill
 ers (e.g.\, an embassy is the Target of a Bombing template). \nThis paper 
 describes an approach to template-based IE that removes this requirement a
 nd performs extraction without knowing the template structure in advance. 
 Our algorithm instead learns the template structure automatically from raw
  text\, inducing template schemas as sets of linked events (e.g.\, bombing
 s include detonate\, set off\, and destroy events) associated with semanti
 c roles. We also solve the standard IE task\, using the induced syntactic 
 patterns to extract role fillers from specific documents. We evaluate on t
 he MUC-4 terrorism dataset and show that we induce template structure very
  similar to hand-created gold structure\, and we extract role fillers with
  an F1 score of .40\, approaching the performance of algorithms that requi
 re full knowledge of the templates."\n\nIt would be presented at ACL2011 a
 nd is available at: \nhttp://www.stanford.edu/~jurafsky/acl2011-chambers-t
 emplates.pdf\n
LOCATION:GS15\, Computer Laboratory
END:VEVENT
END:VCALENDAR