{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T06:47:12Z","timestamp":1792133232176,"version":"4.4.0"},"publisher-location":"New York, NY","reference-count":19,"publisher":"Springer New York","isbn-type":[{"value":"9781461482666","type":"print"},{"value":"9781461482659","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-1-4614-8265-9_596","type":"book-chapter","created":{"date-parts":[[2018,12,6]],"date-time":"2018-12-06T07:07:09Z","timestamp":1544080029000},"page":"1035-1040","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Deduplication in Data Cleaning"],"prefix":"10.1007","author":[{"given":"Raghav","family":"Kaushik","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,12,7]]},"reference":[{"key":"596_CR4848","doi-asserted-by":"crossref","unstructured":"Ananthakrishna R, Chaudhuri S, Ganti V. Eliminating fuzzy duplicates in data warehouses. In: Proceedings of the 28th International Conference on Very Large Data Bases; 2002.","DOI":"10.1016\/B978-155860869-6\/50058-5"},{"key":"596_CR4849","unstructured":"Aslam JA, Pelehov K, Rus D. A practical clustering algorithm for static and dynamic information organization. In: Proceedings of the 10th Annual ACM-SIAM Symposium on Discrete Algorithms; 1999."},{"issue":"1\u20133","key":"596_CR4850","first-page":"89","volume":"56","author":"N Bansal","year":"2002","unstructured":"Bansal N, Blum A, Chawla S. Correlation clustering. Mach Learn. 2002;56(1\u20133):89\u2013113.","journal-title":"Mach Learn"},{"issue":"2","key":"596_CR4851","first-page":"4","volume":"29","author":"I Bhattacharya","year":"2006","unstructured":"Bhattacharya I, Getoor L. Collective entity resolution in relational data. Q Bull IEEE TC Data Eng. 2006;29(2):4\u201312.","journal-title":"Q Bull IEEE TC Data Eng"},{"key":"596_CR4852","doi-asserted-by":"crossref","unstructured":"Bilenko M, Basu S, Mooney RJ. Integrating constraints and metric learning in semi-supervised clustering. In: Proceedings of the 21st International Conference on Machine Learning; 2004.","DOI":"10.1145\/1015330.1015360"},{"key":"596_CR4853","doi-asserted-by":"crossref","unstructured":"Bohannon P, Fan W, Flaster M, Rastogi R. A cost based model and effective heuristic for repairing constraints by value modification. In: Proceedings of the ACM SIGMOD International Conference on Management of Data; 2005.","DOI":"10.1145\/1066157.1066175"},{"issue":"3","key":"596_CR4854","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1016\/j.jcss.2004.10.012","volume":"71","author":"M Charikar","year":"2005","unstructured":"Charikar M, Guruswami V, Wirth A. Clustering with qualitative information. J Comput Syst Sci. 2005;71(3):360\u201383.","journal-title":"J Comput Syst Sci"},{"key":"596_CR4855","doi-asserted-by":"crossref","unstructured":"Chaudhuri S, Sarma A, Ganti V, Kaushik R. Leveraging aggregate constraints for deduplication. In: Proceedings of the ACM SIGMOD International Conference on Management of Data; 2007.","DOI":"10.1145\/1247480.1247530"},{"key":"596_CR4856","doi-asserted-by":"crossref","unstructured":"Dong X, Halevy AY, Madhavan J. Reference reconciliation in complex information spaces. In: Proceedings of the ACM SIGMOD International Conference on Management of Data; 2005.","DOI":"10.1145\/1066157.1066168"},{"key":"596_CR4857","doi-asserted-by":"crossref","unstructured":"Fuxman A, Fazli E, Miller RJ. ConQuer: efficient management of inconsistent databases. In: Proceedings of the ACM SIGMOD International Conference on Management of Data; 2005.","DOI":"10.1145\/1066157.1066176"},{"key":"596_CR4858","unstructured":"Galhardas H, Florescu D, Shasha D, Simon E, Saita C. Declarative data cleaning: language, model, and algorithms. In: Proceedings of the 27th International Conference on Very Large Data Bases; 2001."},{"key":"596_CR4859","doi-asserted-by":"crossref","unstructured":"Koudas N, Sarawagi S, Srivastava D. Record linkage: similarity measures and algorithms. In: Proceedings of the ACM SIGMOD International Conference on Management of Data; 2006.","DOI":"10.1145\/1142473.1142599"},{"key":"596_CR4860","doi-asserted-by":"crossref","unstructured":"Sarawagi S, Bhamidipaty A. Interactive deduplication using active learning. In: Proceedings of the 8th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; 2002.","DOI":"10.1145\/775047.775087"},{"key":"596_CR4861","unstructured":"Single linkage clustering. http:\/\/en.wikipedia.org\/wiki\/Single_linkage_clustering"},{"key":"596_CR4862","unstructured":"The K-means clustering algorithm. http:\/\/mathworld.wolfram.com\/K-MeansClusteringAlgorithm.html"},{"key":"596_CR4863","unstructured":"Trillium software. http:\/\/www.trilliumsoft.com\/trilliumsoft.nsf"},{"issue":"1","key":"596_CR4864","first-page":"25","volume":"11","author":"S Toney","year":"1992","unstructured":"Toney S. Cleanup and deduplication of an international bibliographic database. Inform Tech Lib. 1992;11(1):25.","journal-title":"Inform Tech Lib"},{"key":"596_CR4865","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1007\/3-540-44503-X_26","volume-title":"Database Theory \u2014 ICDT 2001","author":"Anthony K. H. Tung","year":"2001","unstructured":"Tung AKH, Ng RT, Lakshmanan LVS, Han J. Constraint-based clustering in large databases. In: Proceedings of the 8th International Conference on Database Theory; 2001."},{"key":"596_CR4866","unstructured":"Yancey WE. Bigmatch: a program for extracting probable matches from a large file for record linkage. Statistical Research Report Series RRC2002\/01, US Bureau of the Census; 2002."}],"container-title":["Encyclopedia of Database Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-1-4614-8265-9_596","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T06:12:57Z","timestamp":1792131177000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/chapter\/10.1007\/978-1-4614-8265-9_596"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9781461482666","9781461482659"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-1-4614-8265-9_596","relation":{},"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"7 December 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}