BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Unsupervised Machine Learning and Linguistics - Professor Alex Cla
 rk (Royal Holloway\, University of London)
DTSTART:20111201T180000Z
DTEND:20111201T191500Z
UID:TALK34637@talks.cam.ac.uk
CONTACT:26108
DESCRIPTION:The fundamental problem of linguistics is to find how knowledg
 e of language is represented and how that knowledge is acquired by childre
 n learning their first language\; understanding or solving this problem wo
 uld open the door to a new generation of intelligent language processing s
 ystems. This is fundamentally a computational problem\, which can be studi
 ed using the tools of formal language theory and computational learning. S
 olving it requires reconceptualising some basic concepts -- including the 
 relationship between a grammar and the language it defines.\n\nIn this tal
 k I will give an overview of this field (assuming no prior knowledge of li
 nguistics or machine learning) and discuss some recent technical results i
 n distributional learning that can potentially provide a solution to this 
 problem. These techniques involve modelling the relationship between subst
 rings and the contexts that they can appear in -- these give rise to algor
 ithms for learning classes of context free and context sensitive languages
  that seem to be a good match for the properties of natural language.
LOCATION:Winstanley Lecture Hall\, Trinity College
END:VEVENT
END:VCALENDAR