Pairwise document similarity in large collections with MapReduce Export

@inproceedings{citeulike:6079776, abstract = {This paper presents a MapReduce algorithm for computing pairwise document similarity in large document collections. MapReduce is an attractive framework because it allows us to decompose the inner products involved in computing document similarity into separate multiplication and summation stages in a way that is well matched to efficient disk access patterns across several machines. On a collection consisting of approximately 900,000 newswire articles, our algorithm exhibits linear growth in running time and space in terms of the number of documents.}, address = {Morristown, NJ, USA}, author = {Elsayed, Tamer and Lin, Jimmy and Oard, Douglas W.}, booktitle = {HLT '08: Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies}, citeulike-article-id = {6079776}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=1557690.1557767}, keywords = {2008, acl, distributed\_computing, mapreduce}, location = {Columbus, Ohio}, pages = {265--268}, posted-at = {2009-11-06 02:56:44}, priority = {2}, publisher = {Association for Computational Linguistics}, title = {Pairwise document similarity in large collections with MapReduce}, url = {http://portal.acm.org/citation.cfm?id=1557690.1557767}, year = {2008} }

TY - CONF ID - citeulike:6079776 L3 - citeulike-article-id:6079776 N2 - This paper presents a MapReduce algorithm for computing pairwise document similarity in large document collections. MapReduce is an attractive framework because it allows us to decompose the inner products involved in computing document similarity into separate multiplication and summation stages in a way that is well matched to efficient disk access patterns across several machines. On a collection consisting of approximately 900,000 newswire articles, our algorithm exhibits linear growth in running time and space in terms of the number of documents. CY - Columbus, Ohio AD - Morristown, NJ, USA EP - 268 TI - Pairwise document similarity in large collections with MapReduce PB - Association for Computational Linguistics T2 - HLT '08: Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies SP - 265 KW - 2008 KW - acl KW - distributed_computing KW - mapreduce AU - Elsayed, Tamer AU - Lin, Jimmy AU - Oard, Douglas PY - 2008/// UR - http://portal.acm.org/citation.cfm?id=1557690.1557767 ER -