%0 Journal Article %1 lund_producing_1996 %A Lund, Kevin %A Burgess, Curt %D 1996 %J Behavior Research Methods, Instruments, & Computers %K semantik %N 2 %P 203--208 %R 10.3758/BF03204766 %T Producing high-dimensional semantic spaces from lexical co-occurrence %U http://link.springer.com/article/10.3758/BF03204766 %V 28 %X 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).

@article{lund_producing_1996, 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).}, added-at = {2018-11-04T17:02:36.000+0100}, author = {Lund, Kevin and Burgess, Curt}, biburl = {https://www.bibsonomy.org/bibtex/234275296af6da19ad0e7061b4fac28dc/lepsky}, doi = {10.3758/BF03204766}, interhash = {77e182745556c0a24e0e67a22652a66e}, intrahash = {34275296af6da19ad0e7061b4fac28dc}, issn = {0743-3808, 1532-5970}, journal = {Behavior Research Methods, Instruments, \& Computers}, keywords = {semantik}, language = {en}, number = 2, pages = {203--208}, timestamp = {2018-11-04T17:02:36.000+0100}, title = {Producing high-dimensional semantic spaces from lexical co-occurrence}, url = {http://link.springer.com/article/10.3758/BF03204766}, urldate = {2015-09-09}, volume = 28, year = 1996 }