• Seminars & Events
  • Latest
  • Archive
  • RSS Feed

Back

20 March 2008

The Distributional Hypothesis and Context-Theoretic Semantics

Location: Room 308 Maths & Computing Building Top Floor
Time: 12.00- 13.45
Speaker(s): David Weir

Abstract:  The distributional hypothesis asserts that words that occur in similar contexts tend to have similar meanings. A growing body of research has been concerned with exploiting the connection between language use and meaning, and much of this work has involved measuring the distributional similarity of words based on the extent that they share similar contexts. In this talk I  consider a variety of approaches that have been developed to measure distributional similarity, and look more generally at the potential of this approach by considering the following questions. How well can the semantics of a word be localised using distributional similarity?  Is it feasible to use distributional similiarity to compare the meaning, not just of individual words, but of phrases? Can distributional similarity be used to determine ontological relationships such as hyponomy between word senses? Biography:  David Weir is a Reader in Computer Science and Aritificial Intelligence and a member of the Natural Language Processing research group at the University of Sussex. He joined Sussex in 1991 having previously been an Assistant Professor at Northwestern University. He received his PhD in Computer and Information Science from the University of Pennsylvania. 


Save to your Calendar

Contact: mailto:r.power@open.ac.uk