Abstract
This paper presents a series of new results on corpus derived semantic representations based on vectors of simple word co-occurrence statistics, with particular reference to word categorization performance as a function of window type and size, semantic vector dimension, and corpus size. A number of outstanding problems and difficulties with this approach are identified and discussed.
Original language | English |
---|---|
Title of host publication | Proceedings of the ESSLLI Workshop on Distributional Lexical Semantics: |
Subtitle of host publication | Bridging the gap between semantic theory and computational simulations |
Editors | Marco Baroni, Stefan Evert, Alessandro Lenci |
Publisher | University of Hamburg |
Pages | 1-8 |
Number of pages | 8 |
Publication status | Published - 9 Aug 2008 |
Event | ESSLLI Workshop on Distributional Lexical Semantics:: Bridging the gap between semantic theory and computational simulations - Hamburg, Germany Duration: 4 Aug 2008 → 9 Aug 2008 |
Conference
Conference | ESSLLI Workshop on Distributional Lexical Semantics: |
---|---|
Country/Territory | Germany |
City | Hamburg |
Period | 4/08/08 → 9/08/08 |