Syntactic clustering of the Web

@article{broder97syntactic, address = {Essex, UK}, author = {Broder, Andrei Z. and Glassman, Steven C. and Manasse, Mark S. and Zweig, Geoffrey }, booktitle = {Selected papers from the sixth international conference on World Wide Web}, citeulike-article-id = {379517}, comment = {Roughly 1/3 of pages on the web are duplicates. Uses shingles.}, doi = {10.1016/S0169-7552(97)00031-7}, issn = {0169-7552}, journal = {Computer Networks and ISDN Systems}, keywords = {clustering, text}, month = {September}, number = {8-13}, pages = {1157--1166}, posted-at = {2008-06-12 11:10:02}, priority = {2}, publisher = {Elsevier Science Publishers Ltd.}, title = {Syntactic clustering of the Web}, url = {http://portal.acm.org/citation.cfm?id=283370}, volume = {29}, year = {1997} }

TY - JOUR ID - broder97syntactic L3 - citeulike-article-id:379517 TI - Syntactic clustering of the Web T2 - Selected papers from the sixth international conference on World Wide Web JF - Computer Networks and ISDN Systems VL - 29 IS - 8-13 SP - 1157 EP - 1166 AD - Essex, UK PB - Elsevier Science Publishers Ltd. SN - 0169-7552 KW - clustering KW - text N1 - Roughly 1/3 of pages on the web are duplicates. Uses shingles. AU - Broder, Andrei AU - Glassman, Steven AU - Manasse, Mark AU - Zweig, Geoffrey PY - 1997/09// UR - http://portal.acm.org/citation.cfm?id=283370 ER -