BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:A maximum entropy approach to preposition and determiner selection
  - Rachele De Felice\, University of Oxford
DTSTART:20080516T110000Z
DTEND:20080516T120000Z
UID:TALK10734@talks.cam.ac.uk
CONTACT:Johanna Geiss
DESCRIPTION:In this talk\, I present a contextual feature-based approach t
 o the\nautomatic acquisition of preposition and determiner models of use. 
 These\nmodels can associate prepositions and determiners to their context 
 with\n70.12% and 92.15% accuracy respectively for grammatical text.\nPreli
 minary experiments on automatic detection of preposition errors in\nnon-na
 tive English writing achieve up to 60% precision and recall.
LOCATION:SW01 Computer Laboratory
END:VEVENT
END:VCALENDAR