Scatter/Gather: a cluster-based approach to browsing large document collections Export

@inproceedings{Cutting1992, abstract = {Document clustering has not been well received as an information retrieval tool. Objections to its use fall into two main categories: first, that clustering is too slow for large corpora (with running time often quadratic in the number of documents); and second, that clustering does not appreciably improve retrieval. We argue that these problems arise only when clustering is used in an attempt to improve conventional search techniques. However, looking at clustering as an information access tool in its own right obviates these objections, and provides a powerful new access paradigm. We present a document browsing technique that employs document clustering as its primary operation. We also present fast (linear time) clustering algorithms which support this interactive browsing paradigm.}, address = {New York, NY, USA}, author = {Cutting, Douglass R. and Karger, David R. and Pedersen, Jan O. and Tukey, John W.}, booktitle = {SIGIR '92: Proceedings of the 15th annual international ACM SIGIR conference on Research and development in information retrieval}, citeulike-article-id = {437257}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=133214}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/133160.133214}, doi = {10.1145/133160.133214}, isbn = {0-89791-523-2}, keywords = {archives, clustering, documents, hci}, location = {Copenhagen, Denmark}, pages = {318--329}, posted-at = {2006-09-15 20:27:33}, priority = {2}, publisher = {ACM}, title = {Scatter/Gather: a cluster-based approach to browsing large document collections}, url = {http://dx.doi.org/10.1145/133160.133214}, year = {1992} }

TY - CONF ID - Cutting1992 L3 - citeulike-article-id:437257 N2 - Document clustering has not been well received as an information retrieval tool. Objections to its use fall into two main categories: first, that clustering is too slow for large corpora (with running time often quadratic in the number of documents); and second, that clustering does not appreciably improve retrieval. We argue that these problems arise only when clustering is used in an attempt to improve conventional search techniques. However, looking at clustering as an information access tool in its own right obviates these objections, and provides a powerful new access paradigm. We present a document browsing technique that employs document clustering as its primary operation. We also present fast (linear time) clustering algorithms which support this interactive browsing paradigm. CY - Copenhagen, Denmark SN - 0-89791-523-2 AD - New York, NY, USA EP - 329 TI - Scatter/Gather: a cluster-based approach to browsing large document collections PB - ACM T2 - SIGIR '92: Proceedings of the 15th annual international ACM SIGIR conference on Research and development in information retrieval SP - 318 KW - archives KW - clustering KW - documents KW - hci AU - Cutting, Douglass AU - Karger, David AU - Pedersen, Jan AU - Tukey, John PY - 1992/// UR - http://dx.doi.org/10.1145/133160.133214 ER -