BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Unsupervised Learning of Narrative Schemas and their Participants 
 - Diarmuid Ó Séaghdha (University of Cambridge)
DTSTART:20091019T113000Z
DTEND:20091019T123000Z
UID:TALK21072@talks.cam.ac.uk
CONTACT:Diarmuid Ó Séaghdha
DESCRIPTION:At this session of the NLIP Reading Group we'll be discussing 
 the following paper:\n\nNathaniel Chambers and Dan Jurafsky. 2009. "Unsupe
 rvised Learning of Narrative Schemas and their Participants":http://www.ac
 lweb.org/anthology/P/P09/P09-1068.pdf. In Proceedings of ACL-IJCNLP-09.\n\
 n*Abstract:*\nWe describe an unsupervised system for learning narrative sc
 hemas\, coherent sequences or sets of events (arrested(POLICE\,SUSPECT)\, 
 convicted(JUDGE\, SUSPECT)) whose arguments are filled with participant se
 mantic roles defined over words (JUDGE = {judge\, jury\, court}\, POLICE =
  {police\, agent\, authorities}). Unlike most previous work in event struc
 ture or semantic role learning\, our system does not use supervised techni
 ques\, hand-built knowledge\, or predefined classes of events or roles. Ou
 r unsupervised learning algorithm uses coreferring arguments in chains of 
 verbs to learn both rich narrative event structure and argument roles. By 
 jointly addressing both tasks\, we improve on previous results in narrativ
 e/frame learning and induce rich frame-specific semantic roles.\n
LOCATION:GS15\, Computer Laboratory
END:VEVENT
END:VCALENDAR