BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:What Happens Next? Event Prediction Using a Compositional Neural N
 etwork Model - Mark Granroth-Wilding\, Computer Laboratory
DTSTART:20160219T120000Z
DTEND:20160219T130000Z
UID:TALK63498@talks.cam.ac.uk
CONTACT:Kris Cao
DESCRIPTION:We address the problem of automatically acquiring knowledge of
  event sequences from text\, with the aim of providing a predictive model 
 for use in narrative generation systems. We present a neural network model
  that simultaneously learns embeddings for words describing events\, a fun
 ction to compose the embeddings into a representation of the event\, and a
  coherence function to predict the strength of association between two eve
 nts.\n\nWe introduce a new development of the narrative cloze evaluation t
 ask\, better suited to a setting where rich information about events is av
 ailable. We compare models that learn vector-space representations of the 
 events denoted by verbs in chains centering on a single protagonist. We fi
 nd that recent work on learning vector-space embeddings to capture word me
 aning can be effectively applied to this task\, including simple incorpora
 tion of a verb's arguments in the representation by vector addition. These
  representations provide a good initialization for learning the richer\, c
 ompositional model of events with a neural network\, vastly outperforming 
 a number of baselines and competitive alternatives. 
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR