BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Statistical Parsing of Natural Language with Lexicalised Grammars 
 - Stephen Clark - Oxford University
DTSTART:20090114T141500Z
DTEND:20090114T151500Z
UID:TALK15373@talks.cam.ac.uk
CONTACT:Mateja Jamnik
DESCRIPTION:In this talk I will describe the problem of natural language p
 arsing\, and explain why it is such a difficult problem. I will characteri
 se the problem in terms of three main questions: 1) how to obtain a gramma
 r for natural language\; 2) how to obtain all possible parses for an input
  sentence\; and 3) how to use machine learning to obtain a model of parse 
 plausibility. The answer to 1) will focus on Combinatory Categorial Gramma
 r (CCG)\, a 'lexicalised' grammar formalism with a long history in theoret
 ical linguistics. As well as having some desirable linguistic and formal p
 roperties\, I will show that that the use of CCG leads to a surprisingly e
 fficient practical parser. The answer to 2) will focus on standard chart-p
 arsing techniques. The answer to 3) will focus on the perceptron\, a simpl
 e but highly effective method which can be applied to complex structured l
 earning problems.
LOCATION:Lecture Theatre 1\, Computer Laboratory
END:VEVENT
END:VCALENDAR