{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,3]],"date-time":"2025-06-03T04:09:30Z","timestamp":1748923770133,"version":"3.41.0"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2017,2,1]],"date-time":"2017-02-01T00:00:00Z","timestamp":1485907200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Front. Comput. Sci."],"published-print":{"date-parts":[[2017,2]]},"DOI":"10.1007\/s11704-015-5276-6","type":"journal-article","created":{"date-parts":[[2016,4,19]],"date-time":"2016-04-19T05:14:10Z","timestamp":1461042850000},"page":"147-159","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A genetic algorithm based entity resolution approach with active learning"],"prefix":"10.1007","volume":"11","author":[{"given":"Chenchen","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Derong","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yue","family":"Kou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tiezheng","family":"Nie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ge","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,4,7]]},"reference":[{"issue":"2","key":"5276_CR1","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1007\/s11704-013-3903-7","volume":"7","author":"J. C. Chen","year":"2013","unstructured":"Chen J C, Chen Y G, Du X Y, Li C P, Lu J H, Zhao S Y, Zhou X. Big data challenge: a data management perspective. Frontiers of Computer Science, 2013, 7(2): 157\u2013164","journal-title":"Frontiers of Computer Science"},{"issue":"328","key":"5276_CR2","doi-asserted-by":"crossref","first-page":"1183","DOI":"10.1080\/01621459.1969.10501049","volume":"64","author":"I. P. Fellegi","year":"1969","unstructured":"Fellegi I P, Sunter A B. A theory for record linkage. Journal of the American Statistical Association, 1969, 64(328): 1183\u20131210","journal-title":"Journal of the American Statistical Association"},{"issue":"1","key":"5276_CR3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TKDE.2007.250581","volume":"19","author":"A. K. Elmagarmid","year":"2007","unstructured":"Elmagarmid A K, Ipeirotis P G, Verykios V S. Duplicate record detection: a survey. IEEE Transactions on Knowledge and Data Engineering, 2007, 19(1): 1\u201316","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"issue":"2","key":"5276_CR4","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1016\/j.datak.2009.10.003","volume":"69","author":"H. Kopcke","year":"2010","unstructured":"Kopcke H, Rahm E. Frameworks for entity matching: a comparison. Data and Knowledge Engineering, 2010, 69(2): 197\u2013210","journal-title":"Data and Knowledge Engineering"},{"key":"5276_CR5","first-page":"269","volume-title":"Proceedings of the 8th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.","author":"S. Sarawagi","year":"2002","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, 269\u2013278"},{"key":"5276_CR6","first-page":"267","volume-title":"Proceedings of the 2nd ACM SIGKDD International Conference on Knowledge Discovery and DataMining.","author":"A. E. Monge","year":"1996","unstructured":"Monge A E, Elkan C. The field matching problem: algorithms and applications. In: Proceedings of the 2nd ACM SIGKDD International Conference on Knowledge Discovery and DataMining. 1996, 267\u2013270"},{"key":"5276_CR7","first-page":"309","volume-title":"Proceedings of the 4th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.","author":"J. C. Pinheiro","year":"1998","unstructured":"Pinheiro J C, Sun D X. Methods for linking and mining massive heterogeneous databases. In: Proceedings of the 4th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 1998, 309\u2013313"},{"key":"5276_CR8","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1145\/956750.956759","volume-title":"Proceedings of the 9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.","author":"M. Bilenko","year":"2003","unstructured":"Bilenko M, Mooney R J. Adaptive duplicate detection using learnable string similarity measures. In: Proceedings of the 9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2003, 39\u201348"},{"key":"5276_CR9","first-page":"8","volume-title":"Proceedings of the 5th IEEE International Conference on Data Mining.","author":"S. N. Minton","year":"2005","unstructured":"Minton S N, Nanjo C, Knoblock C A, Michalowski M, Michelson M. A heterogeneous field matching method for record linkage. In: Proceedings of the 5th IEEE International Conference on Data Mining. 2005, 8"},{"key":"5276_CR10","first-page":"215","volume-title":"Proceedings of the 11th IEEE Web Information System and Application Conference.","author":"C. Sun","year":"2014","unstructured":"Sun C, Shen D, Kou Y, Nie T, Yu G. ERGP: A Combined Entity Resolution Approach with Genetic Programming. In: Proceedings of the 11th IEEE Web Information System and Application Conference. 2014, 215\u2013220"},{"issue":"3","key":"5276_CR11","first-page":"293","volume":"6","author":"P. Li","year":"2012","unstructured":"Li P, Dong X L, Maurino A, Srivastava D. Linking temporal records. Frontiers of Computer Science, 2012, 6(3): 293\u2013312","journal-title":"Frontiers of Computer Science"},{"key":"5276_CR12","doi-asserted-by":"crossref","first-page":"458","DOI":"10.1007\/978-3-319-18120-2_27","volume-title":"Proceedings of the 20th International Conference on Database Systems for Advanced Applications.","author":"C. C. Sun","year":"2015","unstructured":"Sun C C, Shen D R, Kou Y, Nie T Z, Yu G. GB-JER: A Graph-Based Model for Joint Entity Resolution. In: Proceedings of the 20th International Conference on Database Systems for Advanced Applications. 2015, 458\u2013473"},{"issue":"8","key":"5276_CR13","doi-asserted-by":"crossref","first-page":"607","DOI":"10.1016\/S0306-4379(01)00042-4","volume":"26","author":"S. Tejada","year":"2001","unstructured":"Tejada S, Knoblock C A, Minton S. Learning object identification rules for information integration. Information Systems, 2001, 26(8): 607\u2013633","journal-title":"Information Systems"},{"key":"5276_CR14","volume-title":"Methods for record linkage and bayesian networks","author":"W. E. Winkler","year":"2002","unstructured":"Winkler W E. Methods for record linkage and bayesian networks. Technical report, Series RRS2002\/05. 2002"},{"key":"5276_CR15","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1145\/1141753.1141760","volume-title":"Proceedings of the 6th ACM\/IEEE-CS Joint Conference on Digital Libraries.","author":"M. G. Carvalho De","year":"2006","unstructured":"De Carvalho M G, Gon\u00e7alves M A, Laender A H F, Da Silva A S. Learning to deduplicate. In: Proceedings of the 6th ACM\/IEEE-CS Joint Conference on Digital Libraries. 2006, 41\u201350"},{"key":"5276_CR16","doi-asserted-by":"crossref","first-page":"1801","DOI":"10.1145\/1363686.1364118","volume-title":"Proceedings of the 2008 ACM Symposium on Applied Computing.","author":"M.G. Carvalho De","year":"2008","unstructured":"De Carvalho MG, Laender A H, Gon\u00e7alves MA, Da Silva A S. Replica identification using genetic programming. In: Proceedings of the 2008 ACM Symposium on Applied Computing. 2008, 1801\u20131806"},{"issue":"3","key":"5276_CR17","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1109\/TKDE.2010.234","volume":"24","author":"M. G. Carvalho De","year":"2012","unstructured":"De Carvalho M G, Laender A H, Gon\u00e7alves M A, Da Silva A S. A genetic programming approach to record deduplication. IEEE Transactions on Knowledge and Data Engineering, 2012, 24(3): 399\u2013412","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"5276_CR18","first-page":"13","volume-title":"Proceedings of the 6th International Workshop on Ontology Matching.","author":"R. Isele","year":"2011","unstructured":"Isele R, Bizer C. Learning linkage rules using genetic programming. In: Proceedings of the 6th International Workshop on Ontology Matching. 2011, 13\u201324"},{"issue":"11","key":"5276_CR19","first-page":"1638","volume":"5","author":"R. Isele","year":"2012","unstructured":"Isele R, Bizer C. Learning expressive linkage rules using genetic programming. The Very Large Databases Endowment, 2012, 5(11): 1638\u20131649","journal-title":"The Very Large Databases Endowment"},{"key":"5276_CR20","doi-asserted-by":"crossref","DOI":"10.1007\/BFb0055923","volume-title":"Genetic programming: an introduction","author":"W. Banzhaf","year":"1998","unstructured":"Banzhaf W, Nordin P, Keller R E, Francone F D. Genetic programming: an introduction. San Francisco: Morgan Kaufmann, 1998"},{"key":"5276_CR21","volume-title":"A field guide to genetic programming","author":"R. Poli","year":"2008","unstructured":"Poli R, Langdon W B, McPhee N F, Koza J R. A field guide to genetic programming. Lulu.com, 2008"},{"key":"5276_CR22","first-page":"591","volume-title":"Proceedings of the 14th National Conference on Artificial Intelligence.","author":"R. Liere","year":"1997","unstructured":"Liere R, Tadepalli P. Active learning with committees for text categorization. In: Proceedings of the 14th National Conference on Artificial Intelligence. 1997, 591\u2013596"},{"issue":"2","key":"5276_CR23","first-page":"201","volume":"15","author":"D. Cohn","year":"1994","unstructured":"Cohn D, Atlas L, Ladner R. Improving generalization with active learning. Machine Learning, 1994, 15(2): 201\u2013221","journal-title":"Machine Learning"},{"issue":"3","key":"5276_CR24","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1145\/2513092.2500490","volume":"7","author":"K. Bellare","year":"2013","unstructured":"Bellare K, Suresh I, Parameswaran A, Rastogi V. Active sampling for entity matching with guarantees. ACM Transactions on Knowledge Discovery from Data, 2013, 7(3): 12","journal-title":"ACM Transactions on Knowledge Discovery from Data"},{"key":"5276_CR25","first-page":"783","volume-title":"Proceedings of the 2010 International Conference on Management of Data.","author":"A. Arasu","year":"2010","unstructured":"Arasu A, Gotz M, Kaushik R. On active learning of record matching packages. In: Proceedings of the 2010 International Conference on Management of Data. 2010, 783\u2013794"},{"key":"5276_CR26","volume-title":"Genetic Programming: on the Programming of Computers by Means of Natural Selection","author":"J. R. Koza","year":"1992","unstructured":"Koza J R. Genetic Programming: on the Programming of Computers by Means of Natural Selection. Boston: MIT Press, 1992"},{"key":"5276_CR27","first-page":"73","volume-title":"Proceedings of the 9th ACM SIGKDDWorkshop on Data Cleaning and Object Consolidation.","author":"W. Cohen","year":"2003","unstructured":"Cohen W, Ravikumar P, Fienberg S. A comparison of string metrics for matching names and records. In: Proceedings of the 9th ACM SIGKDDWorkshop on Data Cleaning and Object Consolidation. 2003, 73\u201378"},{"key":"5276_CR28","volume-title":"Modern information retrieval","author":"R. Baeza-Yates","year":"1999","unstructured":"Baeza-Yates R, Ribeiro-Neto B. Modern information retrieval. New York: ACM Press, 1999"},{"key":"5276_CR29","volume-title":"TIK-Report No.11","author":"T. Blickle","year":"1995","unstructured":"Blickle T, Thiele L. A comparison of selection schemes used in genetic algorithms. TIK-Report No.11, 1995"},{"key":"5276_CR30","first-page":"23","volume-title":"Proceedings of the 2nd ACM SIGMOD Workshop Research Issues in Data Mining and Knowledge Discovery.","author":"A. E. Monge","year":"1997","unstructured":"Monge A E, Elkan C P. An efficient domain-independent algorithm for detecting approximately duplicate database records. In: Proceedings of the 2nd ACM SIGMOD Workshop Research Issues in Data Mining and Knowledge Discovery. 1997, 23\u201329"},{"issue":"3","key":"5276_CR31","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1002\/j.1538-7305.1948.tb01338.x","volume":"27","author":"C. E. Shannon","year":"1948","unstructured":"Shannon C E. A mathematical theory of communication. Bell System Technical Journal, 1948, 27(3): 379\u2013423","journal-title":"Bell System Technical Journal"},{"issue":"1","key":"5276_CR32","first-page":"1282","volume":"2","author":"O. Hassanzadeh","year":"2009","unstructured":"Hassanzadeh O, Chiang F, Lee H C, Miller R J. Framework for evaluating clustering algorithms in duplicate detection. The Very Large Databases Endowment, 2009, 2(1): 1282\u20131293","journal-title":"The Very Large Databases Endowment"}],"container-title":["Frontiers of Computer Science"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11704-015-5276-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11704-015-5276-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11704-015-5276-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11704-015-5276-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,2]],"date-time":"2025-06-02T20:14:09Z","timestamp":1748895249000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11704-015-5276-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,2]]},"references-count":32,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2017,2]]}},"alternative-id":["5276"],"URL":"https:\/\/doi.org\/10.1007\/s11704-015-5276-6","relation":{},"ISSN":["2095-2228","2095-2236"],"issn-type":[{"type":"print","value":"2095-2228"},{"type":"electronic","value":"2095-2236"}],"subject":[],"published":{"date-parts":[[2017,2]]}}}