%0 Conference Paper %1 elsayed2008pairwise %A Elsayed, Tamer %A Lin, Jimmy %A Oard, Douglas W. %B Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies: Short Papers %C Stroudsburg, PA, USA %D 2008 %I Association for Computational Linguistics %K hadoop map_reduce pairwise similarity %P 265--268 %T Pairwise document similarity in large collections with MapReduce %U http://dl.acm.org/citation.cfm?id=1557690.1557767 %X 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.

@inproceedings{elsayed2008pairwise, 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.}, acmid = {1557767}, added-at = {2012-09-20T18:08:05.000+0200}, address = {Stroudsburg, PA, USA}, author = {Elsayed, Tamer and Lin, Jimmy and Oard, Douglas W.}, biburl = {https://www.bibsonomy.org/bibtex/2d777aeaa47aaf92636b01997f031b7ac/dbenz}, booktitle = {Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies: Short Papers}, description = {Pairwise document similarity in large collections with MapReduce}, interhash = {928b29114975d5b4b5982f6ef8881d91}, intrahash = {d777aeaa47aaf92636b01997f031b7ac}, keywords = {hadoop map_reduce pairwise similarity}, location = {Columbus, Ohio}, numpages = {4}, pages = {265--268}, publisher = {Association for Computational Linguistics}, series = {HLT-Short '08}, timestamp = {2013-07-31T15:39:42.000+0200}, title = {Pairwise document similarity in large collections with MapReduce}, url = {http://dl.acm.org/citation.cfm?id=1557690.1557767}, year = 2008 }