{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T07:49:03Z","timestamp":1767772143647,"version":"3.44.0"},"reference-count":16,"publisher":"IEEE","license":[{"start":{"date-parts":[[2011,9,1]],"date-time":"2011-09-01T00:00:00Z","timestamp":1314835200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2011,9,1]],"date-time":"2011-09-01T00:00:00Z","timestamp":1314835200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011,9]]},"DOI":"10.1109\/icdke.2011.6053920","type":"proceedings-article","created":{"date-parts":[[2011,10,21]],"date-time":"2011-10-21T11:03:34Z","timestamp":1319195014000},"page":"18-24","source":"Crossref","is-referenced-by-count":19,"title":["A generalization of blocking and windowing algorithms for duplicate detection"],"prefix":"10.1109","author":[{"given":"Uwe","family":"Draisbach","sequence":"first","affiliation":[{"name":"Hasso Plattner Institute, 14482 Potsdam, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Felix","family":"Naumann","sequence":"additional","affiliation":[{"name":"Hasso Plattner Institute, 14482 Potsdam, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Real-world data is dirty: Data cleansing and the merge\/purge problem","volume":"2","author":"mauricio","year":"1998","journal-title":"Data Mining and Knowledge Discovery"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.14778\/1920841.1920871"},{"key":"ref12","article-title":"An efficient domain-independent algorithm for detecting approximately duplicate database records","author":"alvaro","year":"0","journal-title":"Proceedings of the Workshop on Research Issues on Data Mining and"},{"journal-title":"An Introduction to Duplicate Detection (Synthesis Lectures on Data Management)","year":"1997","author":"naumann","key":"ref13"},{"key":"ref14","article-title":"XML duplicate detection using sorted neighborhoods","author":"puhlmann","year":"0","journal-title":"Proceedings of the International Conference on Extending Database Technology (EDBT)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1559845.1559870"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1255175.1255213"},{"key":"ref4","article-title":"Towards parameter-free blocking for scalable record linkage","author":"christen","year":"2007","journal-title":"Technical Report TR-CS-07-03"},{"key":"ref3","article-title":"Adaptive blocking: Learning to scale up record linkage","author":"bilenko","year":"0","journal-title":"Industrial Conference on Data Mining (ICDM)"},{"key":"ref6","article-title":"A comparison and generalization of blocking and windowing algorithms for duplicate detection","author":"draisbach","year":"0","journal-title":"Proceedings of the International Workshop on Quality in Databases (QDB)"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-44918-8_6","article-title":"Quality and complexity measures for data linkage and deduplication","author":"christen","year":"2007","journal-title":"Quality Measures in Data Mining volume 43 of Studies in Computational Intelligence"},{"key":"ref8","article-title":"Duplicate record detection: A survey","volume":"19","author":"ahmed","year":"2007","journal-title":"IEEE Transactions on Knowledge and Data Engineering (TKDE)"},{"key":"ref7","article-title":"DuDe: The duplicate detection toolkit","author":"draisbach","year":"0","journal-title":"Proceedings of the International Workshop on Quality in Databases (QDB)"},{"key":"ref2","article-title":"A comparison of fast blocking methods for record linkage","author":"baxter","year":"0","journal-title":"Proc of ACM SIGKDD'03 Workshop on Data Cleaning Record Linkage and Object Consolidation"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-155860869-6\/50058-5"},{"key":"ref9","article-title":"The merge\/purge problem for large databases","author":"mauricio","year":"0","journal-title":"Proceedings of the International Conference on Management of Data (SIGMOD)"}],"event":{"name":"2011 International Conference on Data and Knowledge Engineering (ICDKE)","start":{"date-parts":[[2011,9,6]]},"location":"Milan, Italy","end":{"date-parts":[[2011,9,6]]}},"container-title":["2011 International Conference on Data and Knowledge Engineering (ICDKE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/6044612\/6053908\/06053920.pdf?arnumber=6053920","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T17:42:21Z","timestamp":1757526141000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/6053920\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,9]]},"references-count":16,"URL":"https:\/\/doi.org\/10.1109\/icdke.2011.6053920","relation":{},"subject":[],"published":{"date-parts":[[2011,9]]}}}