{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T09:49:56Z","timestamp":1773481796681,"version":"3.50.1"},"reference-count":27,"publisher":"Elsevier","isbn-type":[{"value":"9781558608696","type":"print"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2002]]},"DOI":"10.1016\/b978-155860869-6\/50058-5","type":"book-chapter","created":{"date-parts":[[2007,8,9]],"date-time":"2007-08-09T11:32:10Z","timestamp":1186659130000},"page":"586-597","source":"Crossref","is-referenced-by-count":152,"title":["Eliminating Fuzzy Duplicates in Data Warehouses"],"prefix":"10.1016","author":[{"given":"Rohit","family":"Ananthakrishna","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Surajit","family":"Chaudhuri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Venkatesh","family":"Ganti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"4","key":"10.1016\/B978-155860869-6\/50058-5_bib1","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1093\/bioinformatics\/17.4.327","article-title":"A new approach to sequence comparison: Normalized local alignment","volume":"17","author":"Arslan","year":"2001","journal-title":"Bioinformatics"},{"key":"10.1016\/B978-155860869-6\/50058-5_bib2","series-title":"Proceedings of ACM Sigmod Conference","article-title":"Automatic segmentation of text into structured records","author":"Borkar","year":"2001"},{"key":"10.1016\/B978-155860869-6\/50058-5_bib3","series-title":"Proc. Sixth Int'l. World Wide Web Conference, World Wide Web Consortium","first-page":"391","article-title":"Syntactic Clustering of the Web","author":"Broder","year":"1997"},{"key":"10.1016\/B978-155860869-6\/50058-5_bib4","series-title":"International Conference on Database Theory","first-page":"217","article-title":"When is \u201cnearest neighbor\u201d meaningful?","author":"Beyer","year":"1999"},{"key":"10.1016\/B978-155860869-6\/50058-5_bib5","series-title":"Outliers in statistical data","author":"Barnett","year":"1994"},{"key":"10.1016\/B978-155860869-6\/50058-5_bib6","series-title":"Modern Information Retrieval","author":"Baeza-Yates","year":"1999"},{"key":"10.1016\/B978-155860869-6\/50058-5_bib7","series-title":"Proceedings of ACM SIGMOD","first-page":"201","article-title":"Integration of heterogeneous databases without common domains using queries based in textual similarity","author":"Cohen","year":"1998"},{"key":"10.1016\/B978-155860869-6\/50058-5_bib8","series-title":"Data e.quality: A behind the scenes perspective on data cleansing","author":"Forino","year":"2001"},{"key":"10.1016\/B978-155860869-6\/50058-5_bib9","doi-asserted-by":"crossref","first-page":"1183","DOI":"10.1080\/01621459.1969.10501049","article-title":"A theory for record linkage","volume":"64","author":"Felligi","year":"1969","journal-title":"Journal of the American Statistical Society"},{"key":"10.1016\/B978-155860869-6\/50058-5_bib11","series-title":"Proceedings of the 27th International Conference on Very Large Databases","first-page":"371","article-title":"Declarative data cleaning: Language, model, and algorithms","author":"Galhardas","year":"2001"},{"key":"10.1016\/B978-155860869-6\/50058-5_bib12","series-title":"ACM Sigmod","article-title":"An extensible framework for data cleaning","author":"Galhardas","year":"1999"},{"key":"10.1016\/B978-155860869-6\/50058-5_bib13","series-title":"Proceedings of the VLDB","article-title":"Approximate String Joins in a Database (Almost) for Free","author":"Gravano","year":"2001"},{"key":"10.1016\/B978-155860869-6\/50058-5_bib14","series-title":"Proceedings of the ACM SIGKDD fifth international conference on knowledge discovery in databases","first-page":"73","article-title":"Cactus\u2014clustering categorical data using summaries","author":"Ganti","year":"1999"},{"key":"10.1016\/B978-155860869-6\/50058-5_bib15","series-title":"VLDB","article-title":"Clustering categorical data: An approach based on dynamical systems","author":"Gibson","year":"1998"},{"key":"10.1016\/B978-155860869-6\/50058-5_bib16","series-title":"Proceedings of the IEEE International Conference on Data Engineering","article-title":"Rock: A robust clustering algorithm for categorical attributes","author":"Guha","year":"1999"},{"key":"10.1016\/B978-155860869-6\/50058-5_bib17","series-title":"proceedings of the 14th international conference on data engineering (ICDE)","first-page":"392","article-title":"Efficient discovery of functional and approximate dependencies using partitions","author":"Huhtala","year":"1998"},{"key":"10.1016\/B978-155860869-6\/50058-5_bib18","series-title":"Proceedings of the ACM SIGMOD","first-page":"127","article-title":"The merge\/purge problem for large databases","author":"Hernandez","year":"1995"},{"key":"10.1016\/B978-155860869-6\/50058-5_bib19","series-title":"Record linkage techniques \u20141985. Statistics of income division","author":"Kilss","year":"1985"},{"issue":"1","key":"10.1016\/B978-155860869-6\/50058-5_bib20","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1016\/0304-3975(95)00028-U","article-title":"Approximate dependency inference from relations","volume":"149","author":"Kivinen","year":"1995","journal-title":"Theoretical Computer Science"},{"key":"10.1016\/B978-155860869-6\/50058-5_bib21","series-title":"VLDB","first-page":"49","article-title":"Generic Schema Matching with Cupid","author":"Madhavan","year":"2001"},{"key":"10.1016\/B978-155860869-6\/50058-5_bib22","series-title":"Proceedings of the second international conference on knowledge discovery and databases (KDD)","article-title":"The field matching problem: Algorithms and applications","author":"Monge","year":"1996"},{"key":"10.1016\/B978-155860869-6\/50058-5_bib23","series-title":"Proceedings of the SIGMOD Workshop on Data Mining and Knowledge Discovery","article-title":"An efficient domain independent algorithm for detecting approximately duplicate database record","author":"Monge","year":"1997"},{"issue":"1","key":"10.1016\/B978-155860869-6\/50058-5_bib24","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1016\/0169-023X(94)90023-X","article-title":"Algorithms for inferring functional dependencies","volume":"12","author":"Mannila","year":"1994","journal-title":"Data and Knowledge Engineering"},{"key":"10.1016\/B978-155860869-6\/50058-5_bib25","series-title":"Proceedings of the international conference on data quality (IQ)","article-title":"Do metadata models meet iq requirements?","author":"Naumann","year":"1999"},{"issue":"4","key":"10.1016\/B978-155860869-6\/50058-5_bib27","first-page":"3","article-title":"Data cleaning: Problems and current approaches","volume":"23","author":"Rahm","year":"2000","journal-title":"IEEE Data Engineering Bulletin"},{"key":"10.1016\/B978-155860869-6\/50058-5_bib28","series-title":"VLDB","first-page":"381","article-title":"Potter's wheel: An interactive data cleaning system","author":"Raman","year":"2001"},{"key":"10.1016\/B978-155860869-6\/50058-5_bib29","series-title":"Human behaviour and the principle of least effort","author":"Zipf","year":"1949"}],"container-title":["VLDB '02: Proceedings of the 28th International Conference on Very Large Databases"],"original-title":[],"language":"en","deposited":{"date-parts":[[2019,1,5]],"date-time":"2019-01-05T07:59:31Z","timestamp":1546675171000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/B9781558608696500585"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2002]]},"ISBN":["9781558608696"],"references-count":27,"URL":"https:\/\/doi.org\/10.1016\/b978-155860869-6\/50058-5","relation":{},"subject":[],"published":{"date-parts":[[2002]]}}}