BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Learning to Tell Tales: A Data-driven Approach to Story Generation
  - Ekaterina Shutova (University of Cambridge)
DTSTART:20100426T113000Z
DTEND:20100426T123000Z
UID:TALK24594@talks.cam.ac.uk
CONTACT:Diarmuid Ó Séaghdha
DESCRIPTION:At this session of the NLIP Reading Group we’ll be discussin
 g the following paper:\n\nNeil McIntyre and Mirella Lapata. 2009. "Learnin
 g to Tell Tales: A Data-driven Approach to Story Generation":http://www.ac
 lweb.org/anthology/P/P09/P09-1025.pdf. In Proceedings of ACL-IJCNLP-09.\n\
 n*Abstract:*\nComputational story telling has sparked great interest in \n
 artificial intelligence\, partly because of its relevance to educational a
 nd gaming applications. Traditionally\, story generators rely on a large r
 epository of background knowledge containing information about the story p
 lot and its characters. This information is detailed and usually hand craf
 ted. In this paper we propose a data-driven approach for generating short 
 children's stories that does not require extensive manual involvement. We 
 create an end-to-end system that realizes the various components of the ge
 neration pipeline stochastically. Our system follows a generate-and-and-ra
 nk approach where the space of multiple candidate stories is pruned by con
 sidering whether they are plausible\, interesting\, and coherent.
LOCATION:GS15\, Computer Laboratory
END:VEVENT
END:VCALENDAR