BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Using Semantics to help learn Phonetic Categories - Stella Frank\,
  School of Informatics\, University of Edinburgh
DTSTART:20140404T110000Z
DTEND:20140404T120000Z
UID:TALK51321@talks.cam.ac.uk
CONTACT:Tamara Polajnar
DESCRIPTION:Computational models of language acquisition seek to replicate
  human linguistic learning capabilities\, such as an infant's ability to i
 dentify the relevant sound categories in a language.   A key question such
  models can address is which aspects of the input are used to solve a give
 n task: is it more effective to focus on\nonly the most relevant cues\, or
  can integrating cues from other domains be helpful?\nIn this talk I will 
 present an extension of a Bayesian model of phonetic categorisation (Feldm
 an et al.\, 2013).  The original model learns a lexicon as well as phoneti
 c vowel categories\, incorporating the constraint that phonemes appear in 
 word contexts.  However\, it has trouble separating minimal pairs (such as
  'cat'/'caught'/'kite'). Our extension adds further information via situat
 ional context information\, a form of weak semantics or world knowledge\, 
 to disambiguate potential minimal pairs.  This information leads to better
  phonetic categorisation\, especially when the word contexts are degraded.
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR