BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:A Bayesian approach to language learning - Dr Sharon Goldwater (Ed
 inburgh)
DTSTART:20080926T140000Z
DTEND:20080926T150000Z
UID:TALK13709@talks.cam.ac.uk
CONTACT:Zoubin Ghahramani
DESCRIPTION:Children learning language are faced with a difficult task: to
  identify the correct generalizations to draw from highly structured lingu
 istic data\, with little explicit feedback.  What constrains the learner t
 o generalize appropriately?  Research into this question is useful both fo
 r understanding human cognition\, and for improving unsupervised language 
 learning in machines.  In this talk\, I discuss the Bayesian approach to l
 anguage acquisition and describe a nonparametric Bayesian modeling framewo
 rk that can be used to examine a variety of different language learning ta
 sks.  I provide examples from word segmentation (identifying words from co
 ntinuous text or speech) and morphology (identifying stems and suffixes)\,
  showing that these models are successful both in learning from corpora an
 d at modeling human experimental data.
LOCATION:Engineering Department\, CBL Room 438
END:VEVENT
END:VCALENDAR