BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Statistical modelling of metaphor - Ekatarina Shutova\, University
  of Cambridge
DTSTART:20150424T110000Z
DTEND:20150424T120000Z
UID:TALK58364@talks.cam.ac.uk
CONTACT:Tamara Polajnar
DESCRIPTION:Besides making our thoughts more vivid and filling our communi
 cation with richer imagery\, metaphor plays a fundamental structural role 
 in our cognition\, helping us organise and project knowledge. For example\
 , when we say “a well-oiled political machine”\, we view the concept o
 f political system in terms of a mechanism and transfer inferences from th
 e domain of mechanisms onto our reasoning about political processes. Highl
 y frequent in text\, metaphorical language represents a significant challe
 nge for natural language processing (NLP) systems\; and large-scale\, robu
 st and accurate metaphor processing tools are needed to improve the overal
 l quality of semantic interpretation in today's language technology. In th
 is talk I will introduce statistical models of metaphor identification and
  interpretation and discuss how statistical techniques can be applied to i
 dentify patterns of the use of metaphor in linguistic data and to generali
 ze its higher-level mechanisms from text.
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR