Indexing by latent semantic analysis Export

@article{citeulike:203957, abstract = {A new method for automatic indexing and retrieval is described. The approach is to take advantage of implicit higher-order structure in the association of terms with documents (<IMG SRC="/giflibrary/12/ldquo.gif" BORDER="0">semantic structure<IMG SRC="/giflibrary/12/rdquo.gif" BORDER="0">) in order to improve the detection of relevant documents on the basis of terms found in queries. The particular technique used is singular-value decomposition, in which a large term by document matrix is decomposed into a set of ca. 100 orthogonal factors from which the original matrix can be approximated by linear combination. Documents are represented by ca. 100 item vectors of factor weights. Queries are represented as pseudo-document vectors formed from weighted combinations of terms, and documents with supra-threshold cosine values are returned. Initial tests find this completely automatic method for retrieval to be promising. \&copy; 1990 John Wiley \&amp; Sons, Inc.}, author = {Deerwester, Scott and Dumais, Susan T. and Furnas, George W. and Landauer, Thomas K. and Harshman, Richard}, citeulike-article-id = {203957}, citeulike-linkout-0 = {http://dx.doi.org/10.1002/(SICI)1097-4571(199009)41:6%3C391::AID-ASI1%3E3.0.CO;2-9}, citeulike-linkout-1 = {http://www3.interscience.wiley.com/cgi-bin/abstract/10049585/ABSTRACT}, day = {7}, doi = {10.1002/(SICI)1097-4571(199009)41:6%3C391::AID-ASI1%3E3.0.CO;2-9}, issn = {1097-4571}, journal = {Journal of the American Society for Information Science}, keywords = {2003, indexing, lsi, vectorspace}, month = {January}, number = {6}, pages = {391--407}, posted-at = {2009-01-18 20:25:02}, priority = {2}, title = {Indexing by latent semantic analysis}, url = {http://dx.doi.org/10.1002/(SICI)1097-4571(199009)41:6%3C391::AID-ASI1%3E3.0.CO;2-9}, volume = {41}, year = {1999} }

TY - JOUR ID - citeulike:203957 L3 - citeulike-article-id:203957 N2 - A new method for automatic indexing and retrieval is described. The approach is to take advantage of implicit higher-order structure in the association of terms with documents (<IMG SRC="/giflibrary/12/ldquo.gif" BORDER="0">semantic structure<IMG SRC="/giflibrary/12/rdquo.gif" BORDER="0">) in order to improve the detection of relevant documents on the basis of terms found in queries. The particular technique used is singular-value decomposition, in which a large term by document matrix is decomposed into a set of ca. 100 orthogonal factors from which the original matrix can be approximated by linear combination. Documents are represented by ca. 100 item vectors of factor weights. Queries are represented as pseudo-document vectors formed from weighted combinations of terms, and documents with supra-threshold cosine values are returned. Initial tests find this completely automatic method for retrieval to be promising. &copy; 1990 John Wiley &amp; Sons, Inc. IS - 6 JF - Journal of the American Society for Information Science SN - 1097-4571 EP - 407 TI - Indexing by latent semantic analysis VL - 41 SP - 391 KW - 2003 KW - indexing KW - lsi KW - vectorspace AU - Deerwester, Scott AU - Dumais, Susan AU - Furnas, George AU - Landauer, Thomas AU - Harshman, Richard PY - 1999/01/07/ UR - http://dx.doi.org/10.1002/(SICI)1097-4571(199009)41:6%3C391::AID-ASI1%3E3.0.CO;2-9 ER -