A vector space model for automatic indexing Export

@article{citeulike:270732, abstract = {In a document retrieval, or other pattern matching environment where stored entities (documents) are compared with each other or with incoming patterns (search requests), it appears that the best indexing (property) space is one where each entity lies as far away from the others as possible; in these circumstances the value of an indexing system may be expressible as a function of the density of the object space; in particular, retrieval performance may correlate inversely with space density. An approach based on space density computations is used to choose an optimum indexing vocabulary for a collection of documents. Typical evaluation results are shown, demonstating the usefulness of the model.}, address = {New York, NY, USA}, author = {Salton, G. and Wong, A. and Yang, C. S.}, citeulike-article-id = {270732}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=361220}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/361219.361220}, citeulike-linkout-2 = {http://www.cs.umbc.edu/~nicholas/676/p613-salton.pdf}, doi = {10.1145/361219.361220}, issn = {0001-0782}, journal = {Commun. ACM}, keywords = {ir, model, space, vector}, month = {November}, number = {11}, pages = {613--620}, posted-at = {2007-06-19 08:34:49}, priority = {2}, publisher = {ACM}, title = {A vector space model for automatic indexing}, url = {http://dx.doi.org/10.1145/361219.361220}, volume = {18}, year = {1975} }

TY - JOUR ID - citeulike:270732 L3 - citeulike-article-id:270732 N2 - In a document retrieval, or other pattern matching environment where stored entities (documents) are compared with each other or with incoming patterns (search requests), it appears that the best indexing (property) space is one where each entity lies as far away from the others as possible; in these circumstances the value of an indexing system may be expressible as a function of the density of the object space; in particular, retrieval performance may correlate inversely with space density. An approach based on space density computations is used to choose an optimum indexing vocabulary for a collection of documents. Typical evaluation results are shown, demonstating the usefulness of the model. IS - 11 JF - Commun. ACM SN - 0001-0782 AD - New York, NY, USA EP - 620 TI - A vector space model for automatic indexing PB - ACM VL - 18 SP - 613 KW - ir KW - model KW - space KW - vector AU - Salton, G AU - Wong, A AU - Yang, CS PY - 1975/11// UR - http://dx.doi.org/10.1145/361219.361220 ER -