BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:A Structured Vector Space Model for Word Meaning in Context - Diar
 muid Ó Séaghdha (Computer Laboratory)
DTSTART:20090119T123000Z
DTEND:20090119T133000Z
UID:TALK16342@talks.cam.ac.uk
CONTACT:Diarmuid Ó Séaghdha
DESCRIPTION:At this session of the NLIP Reading Group we'll be discussing 
 the following paper:\n\nKatrin Erk and Sebastian Padó. 2008. "A Structure
 d Vector Space Model for Word Meaning in Context":http://aclweb.org/anthol
 ogy-new/D/D08/D08-1094.pdf. In Proceedings of the 2008 Conference on Empir
 ical Methods in Natural Language Processing (EMNLP-08).\n\n*Abstract:*\nWe
  address the task of computing vector space representations for the meanin
 g of word occurrences\, which can vary widely according to context. This t
 ask is a crucial step towards a robust\, vector-based compositional accoun
 t of sentence meaning. We argue that existing models for this task do not 
 take syntactic structure sufficiently into account.\nWe present a novel st
 ructured vector space model that addresses these issues by incorporating t
 he selectional preferences for argument positions. This makes it possible 
 to integrate syntax into the computation of word meaning in context. In ad
 dition\, the model performs at and above the state of the art for modeling
  the contextual adequacy of paraphrases. 
LOCATION:GS15\, Computer Laboratory
END:VEVENT
END:VCALENDAR