Semantic Categorization Using Simple Word Co-occurrence Statistics

John Bullinaria

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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 languageEnglish
Title of host publicationProceedings of the ESSLLI Workshop on Distributional Lexical Semantics:
Subtitle of host publicationBridging the gap between semantic theory and computational simulations
EditorsMarco Baroni, Stefan Evert, Alessandro Lenci
PublisherUniversity of Hamburg
Pages1-8
Number of pages8
Publication statusPublished - 9 Aug 2008
EventESSLLI Workshop on Distributional Lexical Semantics:: Bridging the gap between semantic theory and computational simulations - Hamburg, Germany
Duration: 4 Aug 20089 Aug 2008

Conference

ConferenceESSLLI Workshop on Distributional Lexical Semantics:
Country/TerritoryGermany
CityHamburg
Period4/08/089/08/08

Fingerprint

Dive into the research topics of 'Semantic Categorization Using Simple Word Co-occurrence Statistics'. Together they form a unique fingerprint.

Cite this