BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Detecting Learner Errors in the Choice of Content Words Using Comp
 ositional Distributional Semantics - Ekaterina Kochmar\, University of Cam
 bridge
DTSTART:20140815T113000Z
DTEND:20140815T120000Z
UID:TALK53643@talks.cam.ac.uk
CONTACT:Ekaterina Kochmar
DESCRIPTION:We describe a novel approach to error detection in adjective
 –noun combinations. We present and release a new dataset of annotated er
 rors where the examples are extracted from learner texts and annotated wit
 h error types. We show how compositional distributional semantic approache
 s can be applied to discriminate between correct and incorrect word combin
 ations from learner data. Finally\, we show how the output of the composit
 ional distributional semantic models can be used as features in a classifi
 er yielding good precision and accuracy.
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR