Producing high-dimensional semantic spaces from lexical co-occurrence

return to the website
by Kevin Lund, Curt Burgess
Abstract:
A procedure that processes a corpus of text and produces numeric vectors containing information about its meanings for each word is presented. This procedure is applied to a large corpus of natural language text taken from Usenet, and the resulting vectors are examined to determine what information is contained within them. These vectors provide the coordinates in a high-dimensional space in which word relationships can be analyzed. Analyses of both vector similarity and multidimensional scaling demonstrate that there is significant semantic information carried in the vectors. A comparison of vector similarity with human reaction times in a single-word priming experiment is presented. These vectors provide the basis for a representational model of semantic memory, hyperspace analogue to language (HAL).
Reference:
Producing high-dimensional semantic spaces from lexical co-occurrence (Kevin Lund, Curt Burgess), In Behavior Research Methods, Instruments, & Computers, Springer, volume 28, 1996.
Bibtex Entry:
@article{lund1996producing,
abstract = {A procedure that processes a corpus of text and produces numeric vectors containing information about its meanings for each word is presented. This procedure is applied to a large corpus of natural language text taken from Usenet, and the resulting vectors are examined to determine what information is contained within them. These vectors provide the coordinates in a high-dimensional space in which word relationships can be analyzed. Analyses of both vector similarity and multidimensional scaling demonstrate that there is significant semantic information carried in the vectors. A comparison of vector similarity with human reaction times in a single-word priming experiment is presented. These vectors provide the basis for a representational model of semantic memory, hyperspace analogue to language (HAL).},
author = {Lund, Kevin and Burgess, Curt},
journal = {Behavior Research Methods, Instruments, \& Computers},
keywords = {SML-LIB-BIBLIO,lang:ENG},
mendeley-tags = {SML-LIB-BIBLIO,lang:ENG},
number = {2},
pages = {203--208},
publisher = {Springer},
title = {{Producing high-dimensional semantic spaces from lexical co-occurrence}},
volume = {28},
year = {1996}
}
Powered by bibtexbrowser