BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium : Computational Modelling of Metaphor
DTSTART:20140210T161500
DTEND:20140210T173000
DTSTAMP:20260510T235027Z
UID:cb1f518d6a53b0a758ca4c5a29b2e03e1b45ff7379a5ae85c29e4cd0
CATEGORIES:Conferences - Seminars
DESCRIPTION:Par : Ekaterina Shutova\, UC Berkeley\nIC Faculty candidateAbs
 tract\nBesides making our thoughts more vivid and filling our communicatio
 n with richer imagery\, metaphor plays a fundamental structural role in ou
 r cognition\, helping us organise and project knowledge. For example\, whe
 n we say “a well-oiled political machine”\, we view the concept of pol
 itical system in terms of a mechanism and transfer inferences from the dom
 ain of mechanisms onto our reasoning about political processes. Highly fre
 quent in text\, metaphorical language represents a significant challenge f
 or natural language processing (NLP) systems\; and large-scale\, robust an
 d accurate metaphor processing tools are needed to improve the overall qua
 lity of semantic interpretation in today's language technology.\nIn this t
 alk I will introduce statistical models of metaphor and discuss how statis
 tical techniques (in particular semi-supervised and unsupervised learning)
  can be applied to identify patterns of the use of metaphor in linguistic 
 data and to generalize its higher-level mechanisms from text. I will then 
 show what such systems can tell us about cross-cultural differences and op
 inion differences\, as well as discussing how they can be extended and app
 lied to a range of text processing problems.Biography \nEkaterina Shutova 
 is a Postdoctoral Research Fellow at the International Computer Science In
 stitute (ICSI) and the Institute for Cognitive and Brain Sciences (ICBS) a
 t the University of California\, Berkeley\, USA. Her research is in the ar
 ea of Natural Language Processing with a specific focus on metaphor and hu
 man creativity\, and its computational and cognitive modelling. She is cur
 rently leading the new Metaphor Extraction research team at ICSI\, the goa
 l of which is to create robust and accurate tools that identify metaphoric
 al expressions in unrestricted text using machine learning and statistical
  techniques.\nPreviously\, she was a Research Associate at DTAL and the Co
 mputer Laboratory\, University of Cambridge\, UK\, where she worked on iss
 ues in computational lexical semantics. Ekaterina received her PhD in Comp
 uter Science from the University of Cambridge in 2011 and her doctoral dis
 sertation concerned computational modelling of figurative language. She is
  a recipient of the Google Anita Borg Scholarship and a UK Government Over
 seas Research Students Award. She also serves as an Associate Editor of Co
 gnitive Processing and is co-chairing a series of ACL workshops on Metapho
 r in NLP.More information
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR