{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T06:52:31Z","timestamp":1760597551828,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2012,10,29]],"date-time":"2012-10-29T00:00:00Z","timestamp":1351468800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2012,10,29]]},"DOI":"10.1145\/2396761.2398403","type":"proceedings-article","created":{"date-parts":[[2012,11,15]],"date-time":"2012-11-15T16:38:00Z","timestamp":1352997480000},"page":"1055-1064","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":17,"title":["An automatic blocking mechanism for large-scale de-duplication tasks"],"prefix":"10.1145","author":[{"given":"Anish","family":"Das Sarma","sequence":"first","affiliation":[{"name":"Google Research, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ankur","family":"Jain","sequence":"additional","affiliation":[{"name":"Yahoo! Research, Santa Clara, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ashwin","family":"Machanavajjhala","sequence":"additional","affiliation":[{"name":"Duke University, Durham, NC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philip","family":"Bohannon","sequence":"additional","affiliation":[{"name":"Facebook, Palo Alto, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2012,10,29]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"DBPedia. http:\/\/dbpedia.org\/.  DBPedia. http:\/\/dbpedia.org\/."},{"key":"e_1_3_2_1_2_1","unstructured":"IMDb: The Internet Movie Database. http:\/\/www.imdb.com.  IMDb: The Internet Movie Database. http:\/\/www.imdb.com."},{"key":"e_1_3_2_1_3_1","unstructured":"MAHOUT. http:\/\/cwiki.apache.org\/MAHOUT\/canopy-clustering.html.  MAHOUT. http:\/\/cwiki.apache.org\/MAHOUT\/canopy-clustering.html."},{"key":"e_1_3_2_1_4_1","volume-title":"KDD","author":"Baxter R.","year":"2003","unstructured":"R. Baxter , P. Christen , and T. Churches . A comparison of fast blocking methods for record linkage . In KDD , 2003 . R. Baxter, P. Christen, and T. Churches. A comparison of fast blocking methods for record linkage. In KDD, 2003."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778-008-0098-x"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2006.13"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2011.127"},{"key":"e_1_3_2_1_9_1","unstructured":"P. Christen and T. C. Febrl. Freely extensible biomedical record linkage manual. http:\/\/datamining.anu.edu.au\/linkage.html 2 2003.  P. Christen and T. C. Febrl. Freely extensible biomedical record linkage manual. http:\/\/datamining.anu.edu.au\/linkage.html 2 2003."},{"key":"e_1_3_2_1_10_1","volume-title":"Discrete-variable extremum problems. Operations Research, 5(2)","author":"Dantzig G. B.","year":"1957","unstructured":"G. B. Dantzig . Discrete-variable extremum problems. Operations Research, 5(2) , 1957 . G. B. Dantzig. Discrete-variable extremum problems. Operations Research, 5(2), 1957."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2007.9"},{"issue":"2283","key":"e_1_3_2_1_12_1","volume":"64","author":"Fellegi I. P.","year":"1969","unstructured":"I. P. Fellegi and A. B. Sunter . A theory for record linkage. Journal of the American Statistical Society , 64 ( 2283 ), 1969 . I. P. Fellegi and A. B. Sunter. A theory for record linkage. Journal of the American Statistical Society, 64(2283), 1969.","journal-title":"Journal of the American Statistical Society"},{"key":"e_1_3_2_1_13_1","volume-title":"Computers and Intractability","author":"Garey M. R.","year":"1979","unstructured":"M. R. Garey and D. S. Johnson . Computers and Intractability . W. H. Freeman and Company , 1979 . M. R. Garey and D. S. Johnson. Computers and Intractability. W. H. Freeman and Company, 1979."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/568271.223807"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.5555\/1315451.1315455"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"M. A. Jaro. Advances in record linkage methodology as applied to matching the 1985 census of tampa. JASA 84 1989.  M. A. Jaro. Advances in record linkage methodology as applied to matching the 1985 census of tampa. JASA 84 1989.","DOI":"10.1080\/01621459.1989.10478785"},{"key":"e_1_3_2_1_17_1","volume-title":"DASFAA","author":"Jin L.","year":"2003","unstructured":"L. Jin , C. Li , and S. Mehrotra . Efficient record linkage in large data sets . In DASFAA , 2003 . L. Jin, C. Li, and S. Mehrotra. Efficient record linkage in large data sets. In DASFAA, 2003."},{"key":"e_1_3_2_1_18_1","volume-title":"Record Linkage Techniques","author":"Kelley R. P.","year":"1985","unstructured":"R. P. Kelley . Advances in record linkage methodology: a method for determining the best blocking strategy . Record Linkage Techniques , 1985 . R. P. Kelley. Advances in record linkage methodology: a method for determining the best blocking strategy. Record Linkage Techniques, 1985."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/1142473.1142599"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/347090.347123"},{"key":"e_1_3_2_1_21_1","volume-title":"AAAI","author":"Michelson M.","year":"2006","unstructured":"M. Michelson and C. A. Knoblock . Learning blocking schemes for record linkage . In AAAI , 2006 . M. Michelson and C. A. Knoblock. Learning blocking schemes for record linkage. In AAAI, 2006."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1989323.1989423"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.5555\/1786574.1786605"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/775047.775087"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/1321440.1321482"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/1807167.1807222"},{"key":"e_1_3_2_1_27_1","volume-title":"Proc. of IJCAI","author":"Cohen S. E. F. W.","year":"2003","unstructured":"S. E. F. W. Cohen , P. Ravikumar . A comparison of string distance metrics for name-matching tasks . In Proc. of IJCAI , 2003 . S. E. F. W. Cohen, P. Ravikumar. A comparison of string distance metrics for name-matching tasks. In Proc. of IJCAI, 2003."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/1559845.1559870"},{"key":"e_1_3_2_1_29_1","volume-title":"Overview of record linkage and current research directions. Statistical Research Division","author":"Winkler W.","year":"2006","unstructured":"W. Winkler . Overview of record linkage and current research directions. Statistical Research Division , U.S. Bureau of the Census, Tech. Report, 2006 . W. Winkler. Overview of record linkage and current research directions. Statistical Research Division, U.S. Bureau of the Census, Tech. Report, 2006."}],"event":{"name":"CIKM'12: 21st ACM International Conference on Information and Knowledge Management","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Maui Hawaii USA","acronym":"CIKM'12"},"container-title":["Proceedings of the 21st ACM international conference on Information and knowledge management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2396761.2398403","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2396761.2398403","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T09:34:39Z","timestamp":1750239279000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2396761.2398403"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,10,29]]},"references-count":28,"alternative-id":["10.1145\/2396761.2398403","10.1145\/2396761"],"URL":"https:\/\/doi.org\/10.1145\/2396761.2398403","relation":{},"subject":[],"published":{"date-parts":[[2012,10,29]]},"assertion":[{"value":"2012-10-29","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}