Using Linear Algebra for Intelligent Information Retrieval Export

@article{Berry1995ir, abstract = {Currently, most approaches to retrieving textual materials from scientific databases depend on a lexical match between words in users' requests and those in or assigned to documents in a database. Because of the tremendous diversity in the words people use to describe the same document, lexical methods are necessarily incomplete and imprecise. Using the singular value decomposition (SVD), one can take advantage of the implicit higher-order structure in the association of terms with documents by determining the SVD of large sparse term by document matrices. Terms and documents represented by 200-300 of the largest singular vectors are then matched against user queries. We call this retrieval method latent semantic indexing (LSI) because the subspace represents important associative relationships between terms and documents that are not evident in individual documents. LSI is a completely automatic yet intelligent indexing method, widely applicable, and a promising way to improve users' access to many kinds of textual materials, or to documents and services for which textual descriptions are available. A survey of the computational requirements for managing LSI-encoded databases as well as current and future applications of LSI is presented.}, author = {Berry, Michael W. and Dumais, Susan T. and O'Brien, Gavin W.}, citeulike-article-id = {779002}, citeulike-linkout-0 = {http://www.jstor.org/stable/2132906}, journal = {SIAM Review}, keywords = {algebra, information, linear, retrieval}, number = {4}, pages = {573--595}, posted-at = {2008-03-14 08:04:45}, priority = {2}, title = {Using Linear Algebra for Intelligent Information Retrieval}, url = {http://www.jstor.org/stable/2132906}, volume = {37}, year = {1995} }

TY - JOUR ID - Berry1995ir L3 - citeulike-article-id:779002 N2 - Currently, most approaches to retrieving textual materials from scientific databases depend on a lexical match between words in users' requests and those in or assigned to documents in a database. Because of the tremendous diversity in the words people use to describe the same document, lexical methods are necessarily incomplete and imprecise. Using the singular value decomposition (SVD), one can take advantage of the implicit higher-order structure in the association of terms with documents by determining the SVD of large sparse term by document matrices. Terms and documents represented by 200-300 of the largest singular vectors are then matched against user queries. We call this retrieval method latent semantic indexing (LSI) because the subspace represents important associative relationships between terms and documents that are not evident in individual documents. LSI is a completely automatic yet intelligent indexing method, widely applicable, and a promising way to improve users' access to many kinds of textual materials, or to documents and services for which textual descriptions are available. A survey of the computational requirements for managing LSI-encoded databases as well as current and future applications of LSI is presented. IS - 4 JF - SIAM Review EP - 595 TI - Using Linear Algebra for Intelligent Information Retrieval VL - 37 SP - 573 KW - algebra KW - information KW - linear KW - retrieval AU - Berry, Michael AU - Dumais, Susan AU - O'Brien, Gavin PY - 1995/// UR - http://www.jstor.org/stable/2132906 ER -