{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T22:33:44Z","timestamp":1767825224356,"version":"3.49.0"},"publisher-location":"Berlin, Heidelberg","reference-count":100,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642229121","type":"print"},{"value":"9783642229138","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011]]},"DOI":"10.1007\/978-3-642-22913-8_18","type":"book-chapter","created":{"date-parts":[[2011,9,24]],"date-time":"2011-09-24T08:56:57Z","timestamp":1316854617000},"page":"385-412","source":"Crossref","is-referenced-by-count":9,"title":["Data De-duplication: A Review"],"prefix":"10.1007","author":[{"given":"Gianni","family":"Costa","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alfredo","family":"Cuzzocrea","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giuseppe","family":"Manco","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Riccardo","family":"Ortale","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Agichtein, E., Ganti, V.: Mining Reference Tables for Automatic Text Segmentation. In: Proc. of ACM SIGKDD Int. Conf. On Knowledge Discovery and Data Mining, Seattle, Washington, USA, pp. 20\u201329 (2004)","DOI":"10.1145\/1014052.1014058"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Ananthakrishna, R., Chaudhuri, S., Ganti, V.: Eliminating Fuzzy Duplicates in Data Warehouses. In: Proc. of Int. Conf. on Very Large Databases, Hong Kong, China, pp. 586\u2013597 (2002)","DOI":"10.1016\/B978-155860869-6\/50058-5"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Andoni, A., Indyk, P.: Near-Optimal Hashing Algorithms for Approximate Nearest Neighbor in High Dimensions. In: Proc. of IEEE Symposium on Foundations of Computer Science, Las Vegas, Nevada, USA, pp. 459\u2013468 (2006)","DOI":"10.1109\/FOCS.2006.49"},{"issue":"1","key":"18_CR4","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1145\/1327452.1327494","volume":"51","author":"A. Andoni","year":"2008","unstructured":"Andoni, A., Indyk, P.: Near-optimal Hashing Algorithms for Approximate Nearest Neighbor in High Dimensions. Communications of the ACM\u00a051(1), 117\u2013122 (2008)","journal-title":"Communications of the ACM"},{"key":"18_CR5","unstructured":"Arasu, A., Ganti, V., Kaushik, R.: Efficient Exact Set-Similarity Joins. In: Proc. of Int. Conf. on Very Large Databases, Seoul, Korea, pp. 918\u2013929 (2006)"},{"key":"18_CR6","doi-asserted-by":"publisher","first-page":"954","DOI":"10.1126\/science.130.3381.954","volume":"130","author":"S.J. Axford","year":"1959","unstructured":"Axford, S.J., Newcombe, H.B., Kennedy, J.M., James, A.P.: Automatic Linkage of Vital Records. Science\u00a0130, 954\u2013959 (1959)","journal-title":"Science"},{"key":"18_CR7","volume-title":"Modern Information Retrieval","author":"R. Baeza-Yates","year":"1999","unstructured":"Baeza-Yates, R., Ribeiro-Neto, B.: Modern Information Retrieval. Addison-Wesley, Reading (1999)"},{"issue":"1-3","key":"18_CR8","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1023\/B:MACH.0000033116.57574.95","volume":"56","author":"N. Bansal","year":"2004","unstructured":"Bansal, N., Blum, A., Chawla, S.: Correlation Clustering. Machine Learning\u00a056(1-3), 89\u2013113 (2004)","journal-title":"Machine Learning"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Bawa, M., Tyson Condie, S., Ganesan, P.: LSH Forest: Self-Tuning Indexes for Similarity Search. In: Proc. of Int. Conf. on World Wide Web, Chiba, Japan, pp. 651\u2013660 (2005)","DOI":"10.1145\/1060745.1060840"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Bayardo, R.J., Srikant, R., Ma, Y.: Scaling Up All Pairs Similarity Search. In: Proc. of Int. Conf. on World Wide Web, Banff, Alberta, Canada, pp. 131\u2013140 (2007)","DOI":"10.1145\/1242572.1242591"},{"issue":"1","key":"18_CR11","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1007\/s00778-008-0098-x","volume":"18","author":"O. Benjelloun","year":"2009","unstructured":"Benjelloun, O., Garcia-Molina, H., Menestrina, D., Su, Q., Whang, S.E., Widom, J.: Swoosh: a generic approach to entity resolution. VLDB Journal\u00a018(1), 255\u2013276 (2009)","journal-title":"VLDB Journal"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Berson, T.A.: Differential Cryptanalysis Mod 232 with Applications to MD5. In: Proc. of Ann. Conf. on Theory and Applications of Cryptographic Techniques, pp. 71\u201380 (1992)","DOI":"10.1007\/3-540-47555-9_6"},{"issue":"1","key":"18_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1217299.1217300","volume":"1","author":"I. Bhattacharya","year":"2007","unstructured":"Bhattacharya, I., Getoor, L.: Collective Entity Resolution in Relational Data. ACM Trans. Knowl. Discovery from Data\u00a01(1), 1\u201335 (2007)","journal-title":"ACM Trans. Knowl. Discovery from Data"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Bhattacharya, I., Getoor, L., Licamele, Louis: QueryTime Entity Resolution. In: Proc. of ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, Philadelphia, Pennsylvania, USA, pp. 529\u2013534 (2006)","DOI":"10.1145\/1150402.1150463"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Bilenko, M., Mooney, R.J.: Adaptive Duplicate Detection Using Learnable String Similarity Measures. In: Proc. of ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, Washington, DC, USA, pp. 39\u201348 (2003)","DOI":"10.1145\/956750.956759"},{"key":"18_CR16","unstructured":"Christen, P.: Towards Parameter-free Blocking for Scalable Record Linkage. Tech. Rep. TR-CS-07-03, Australian National University, Canberra, Australia (2007)"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Christen, P.: Febrl - An Open Source Data Cleaning, Deduplication and Record Linkage System with a Graphical User Interface. In: Proc. of ACM Int. Conf. on Knowledge Discovery and Data Mining, pp. 1065\u20131068 (2008)","DOI":"10.1145\/1401890.1402020"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Borkar, V.R., Deshmukh, K., Sarawagi, S.: Automatic Segmentation of Text into Structured Records. In: Proc. of ACM SIGMOD Int. Conf. on Management of Data, Santa Barbara, California, USA, pp. 175\u2013186 (2001)","DOI":"10.1145\/375663.375682"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Broder, A., Charikar, M., Frieze, A.M., Mitzenmacher, M.: Minwise Independent Permutations. In: Proc. of ACM Symposium on Theory of Computing, Dallas, Texas, USA, pp. 327\u2013336 (1998)","DOI":"10.1145\/276698.276781"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Broder, A., Glassman, S., Manasse, M., Zweig, G.: Syntactic Clustering on the Web. In: Proc. of Int. Conf. on World Wide Web, Santa Clara, California, USA, pp. 1157\u20131166 (1997)","DOI":"10.1016\/S0169-7552(97)00031-7"},{"issue":"3","key":"18_CR21","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1007\/s10115-007-0085-3","volume":"15","author":"E. Cesario","year":"2008","unstructured":"Cesario, E., Folino, F., Locane, A., Manco, G., Ortale, R.: Boosting Text Segmentation Via Progressive Classification. Knowl. and Inf. Syst.\u00a015(3), 285\u2013320 (2008)","journal-title":"Knowl. and Inf. Syst."},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Chaudhuri, S., Ganjam, K., Ganti, V., Motwani, R.: Robust and Efficient Fuzzy Match for Online Data Cleaning. In: Proc. of ACM SIGMOD Conf. on Management of Data, San Diego, California, USA, pp. 313\u2013324 (2003)","DOI":"10.1145\/872757.872796"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Chaudhuri, S., Ganti, V., Motwani, R.: Robust Identification of Fuzzy Duplicates. In: Proc. of Int. Conf. on Data Engineering, Tokyo, Japan, pp. 865\u2013876 (2005)","DOI":"10.1109\/ICDE.2005.125"},{"issue":"3","key":"18_CR24","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1145\/502807.502808","volume":"33","author":"E. Chavez","year":"2001","unstructured":"Chavez, E., Navarro, G., Baeza-Yates, R., Marroquin, J.L.: Searching in Metric Spaces. ACM Comput. Surv.\u00a033(3), 273\u2013321 (2001)","journal-title":"ACM Comput. Surv."},{"key":"18_CR25","unstructured":"Ciaccia, P., Patella, M., Zezula, P.: M-Tree: An Efficient Access Method for Similarity Search in Metric Spaces. In: Proc. of Int. Conf. on Very Large Databases, Athens, Greece, pp. 426\u2013435 (1997)"},{"key":"18_CR26","unstructured":"Cochinwala, M., Dalal, S., Elmagarmid, A.K., Verykios, V.S.: Record Matching: Past, Present and Future. Technical Report, number CSD-TR #01-013. Department of Computer Sciences, Purdue University (2001)"},{"issue":"1-4","key":"18_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/S0020-0255(00)00070-0","volume":"137","author":"M. Cochinwala","year":"2001","unstructured":"Cochinwala, M., Kurien, V., Lalk, G., Shasha, D.: Efficient Data Reconciliation. Information Sciences\u00a0137(1-4), 1\u201315 (2001)","journal-title":"Information Sciences"},{"issue":"3","key":"18_CR28","doi-asserted-by":"crossref","first-page":"228","DOI":"10.1145\/352595.352598","volume":"18","author":"W.W. Cohen","year":"2000","unstructured":"Cohen, W.W.: Data Integration using Similarity Joins and a Word-based Information Representation Language. ACM Trans. on Inf. Syst.\u00a018(3), 228\u2013321 (2000)","journal-title":"ACM Trans. on Inf. Syst."},{"key":"18_CR29","unstructured":"Cohen, W.W., Ravikumar, P., Fienberg, S.E.: A Comparison of String Distance Metrics for Name-Matching Tasks. In: Proc. of IJCAI Workshop on Information Integration on the Web, Acapulco, Mexico, pp. 73\u201378 (2003)"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Cohen, W.W., Richman, J.: Learning to Match and Cluster Large High-Dimensional Data Sets for Data Integration. In: Proc. of ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, Edmonton, Alberta, Canada, pp. 475\u2013480 (2002)","DOI":"10.1007\/3-540-47887-6"},{"issue":"2","key":"18_CR31","first-page":"201","volume":"15","author":"D.A. Cohn","year":"1994","unstructured":"Cohn, D.A., Atlas, L., Ladner, R.E.: Improving Generalization with Active Learning. Machine Learning\u00a015(2), 201\u2013221 (1994)","journal-title":"Machine Learning"},{"issue":"1","key":"18_CR32","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1007\/s10618-009-0155-0","volume":"20","author":"G. Costa","year":"2010","unstructured":"Costa, G., Manco, G., Ortale, R.: An Incremental Clustering Scheme for Data De-duplication. Data Min. and Knowl. Discovery\u00a020(1), 152\u2013187 (2010)","journal-title":"Data Min. and Knowl. Discovery"},{"key":"18_CR33","unstructured":"Database Group Leipzig. Benchmark datasets for entity resolution, http:\/\/dbs.uni-leipzig.de\/en\/research\/projects\/object_matching\/fever\/benchmark_datasets_for_entity_resolution"},{"issue":"1","key":"18_CR34","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","volume":"39","author":"A.P. Dempster","year":"2001","unstructured":"Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum Likelihood from Incomplete Data via the EM Algorithm. Journal of the Royal Statistical Society, Series B\u00a039(1), 1\u201328 (2001)","journal-title":"Journal of the Royal Statistical Society, Series B"},{"key":"18_CR35","doi-asserted-by":"crossref","unstructured":"Dittrich, J.-P., Seeger, B.: Data Redundancy and Duplicate Detection in Spatial Join Processing. In: Proc. of IEEE Int. Conf. on Data Engineering, pp. 535\u2013546 (2000)","DOI":"10.1109\/ICDE.2000.839452"},{"issue":"1","key":"18_CR36","doi-asserted-by":"publisher","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 Transanctions on Knowledge and Data Engineering\u00a019(1), 1\u201316 (2007)","journal-title":"IEEE Transanctions on Knowledge and Data Engineering"},{"key":"18_CR37","unstructured":"Ester, M., Kriegel, H.P., Sander, J., Xu, X.: A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise. In: Proc. of Int. Conf. on Knowledge Discovery and Data Mining, Portland, Oregon, USA, pp. 226\u2013231 (1996)"},{"issue":"11","key":"18_CR38","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1145\/240455.240464","volume":"39","author":"U. Fayyad","year":"1996","unstructured":"Fayyad, U., Piatetsky-Shapiro, G., Smyth, P., Widener, T.: The KDD Process for Extracting Useful Knowledge from Volumes of Data. Communications of the ACM\u00a039(11), 27\u201334 (1996)","journal-title":"Communications of the ACM"},{"key":"18_CR39","doi-asserted-by":"publisher","first-page":"1183","DOI":"10.2307\/2286061","volume":"64","author":"I.P. Fellegi","year":"1969","unstructured":"Fellegi, I.P., Sunter, A.B.: A Theory for Record Linkage. Am. Stat. Assoc.\u00a064, 1183\u20131210 (1969)","journal-title":"Am. Stat. Assoc."},{"key":"18_CR40","doi-asserted-by":"crossref","unstructured":"Ganti, V., Ramakrishnan, R., Gehrke, J., Powell, A.: Clustering Large Datasets in Arbitrary Metric Spaces. In: Proc. of Int. Conf. on Data Engineering, Sydney, Austrialia, pp. 502\u2013511 (1999)","DOI":"10.1109\/ICDE.1999.754966"},{"key":"18_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-540-30464-7_1","volume-title":"Conceptual Modeling \u2013 ER 2004","author":"H. Garcia-Molina","year":"2004","unstructured":"Garcia-Molina, H.: Entity resolution: Overview and challenges. In: Atzeni, P., Chu, W., Lu, H., Zhou, S., Ling, T.-W. (eds.) ER 2004. LNCS, vol.\u00a03288, pp. 1\u20132. Springer, Heidelberg (2004)"},{"key":"18_CR42","volume-title":"Markov Chain Monte Carlo in Practice","author":"W.R. Gilks","year":"1996","unstructured":"Gilks, W.R., Richardson, S., Spiegelhalter, D.J.: Markov Chain Monte Carlo in Practice. Chapman and Hall, Boca Raton (1996)"},{"key":"18_CR43","unstructured":"Gionis, A., Indyk, P., Motwani, R.: Similarity Search in High Dimensions via Hashing. In: Proc. of Int. Conf. on Very Large Databases, Edinburgh, Scotland, pp. 518\u2013529 (1999)"},{"key":"18_CR44","unstructured":"Goiser, K., Christen, P.: Towards Automated Record Linkage. In: Proc. of Australasian Data Mining Conf., pp. 23\u201331 (2006)"},{"issue":"4","key":"18_CR45","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1023\/A:1016308404627","volume":"6","author":"J. Grabmeier","year":"2002","unstructured":"Grabmeier, J., Rudolph, A.: Techniques of Cluster Algorithms in Data Mining. Data Min. and Knowl. Discovery\u00a06(4), 303\u2013360 (2002)","journal-title":"Data Min. and Knowl. Discovery"},{"key":"18_CR46","unstructured":"Gravano, L., Ipeirotis, P.G., Jagadish, H.V., Koudas, N., Muthukrishnan, S., Srivastava, D.: Approximate String Joins in a Database (Almost) for Free. In: Proc of Int. Conf. on Very Large Databases, Rome, Italy, pp. 491\u2013500 (2001)"},{"key":"18_CR47","unstructured":"Gu, L., Baxter, R.A., Vickers, D., Rainsford, C.: Record Linkage: Current Practice and Future Directions. Technical Report, number 03\/83. CSIRO Mathematical and Information Sciences (2001)"},{"key":"18_CR48","doi-asserted-by":"crossref","unstructured":"Guha, S., Rastogi, R., Shim, K.: CURE: An Efficient Clustering Algorithm for Large Databases. In: Proc. of ACM SIGMOD Int. Conf. on Management of Data, Seattle, Washington, USA, pp. 73\u201384 (1998)","DOI":"10.1145\/276304.276312"},{"issue":"5","key":"18_CR49","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1016\/S0306-4379(00)00022-3","volume":"25","author":"S. Guha","year":"2001","unstructured":"Guha, S., Rastogi, R., Shim, K.: ROCK: A Robust Clustering Algorithm for Categorical Attributes. Inf. Syst.\u00a025(5), 345\u2013366 (2001)","journal-title":"Inf. Syst."},{"key":"18_CR50","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511574931","volume-title":"Algorithms on Strings, Trees and Sequences","author":"D. Gunsfield","year":"1997","unstructured":"Gunsfield, D.: Algorithms on Strings, Trees and Sequences. Cambridge University Press, Davis (1997)"},{"issue":"1","key":"18_CR51","doi-asserted-by":"crossref","first-page":"1282","DOI":"10.14778\/1687627.1687771","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. Proceedings of VLDB\u00a02(1), 1282\u20131293 (2009)","journal-title":"Proceedings of VLDB"},{"issue":"5","key":"18_CR52","doi-asserted-by":"publisher","first-page":"1141","DOI":"10.1007\/s00778-009-0161-2","volume":"18","author":"O. Hassanzadeh","year":"2009","unstructured":"Hassanzadeh, O., Miller, R.J.: Creating Probabilistic Databases from Duplicated Data. The VLDB Journal\u00a018(5), 1141\u20131166 (2009)","journal-title":"The VLDB Journal"},{"key":"18_CR53","doi-asserted-by":"crossref","unstructured":"Hern\u00e1ndez, M.A., Stolfo, S.J.: The Merge\/Purge Problem for Large Databases. In: Proc. of ACM SIGMOD Int. Conf. on Management of Data, San Jose, California, USA, pp. 127\u2013138 (1995)","DOI":"10.1145\/568271.223807"},{"issue":"1","key":"18_CR54","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1023\/A:1009761603038","volume":"2","author":"M.A. Hern\u00e1ndez","year":"1998","unstructured":"Hern\u00e1ndez, M.A., Stolfo, J.: Real-world Data is Dirty: Data Cleansing and the Merge\/Purge Problem. Data Min. and Knowl. Discovery\u00a02(1), 9\u201337 (1998)","journal-title":"Data Min. and Knowl. Discovery"},{"key":"18_CR55","doi-asserted-by":"crossref","unstructured":"Herschel, M., Naumann, N.: Scaling up Duplicate Detection in Graph Data. In: Proc. of ACM Int. Conf. on Information and Knowledge Management, pp. 1325\u20131326 (2008)","DOI":"10.1145\/1458082.1458259"},{"issue":"4","key":"18_CR56","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1145\/958942.958948","volume":"28","author":"G.R. Hjatason","year":"2003","unstructured":"Hjatason, G.R., Samet, H.: Index-Driven Similarity Search in Metric Spaces. ACM Trans. on Database Syst.\u00a028(4), 517\u2013518 (2003)","journal-title":"ACM Trans. on Database Syst."},{"key":"18_CR57","doi-asserted-by":"crossref","unstructured":"Indyk, P., Motwani, R.: Approximate Nearest Neighbor - Towards Removing the Curse of Dimensionality. In: Proc. of Symposium on Theory of Computing, Dallas, Texas, USA, pp. 604\u2013613 (1998)","DOI":"10.1145\/276698.276876"},{"issue":"1","key":"18_CR58","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TKDE.2007.250581","volume":"19","author":"P.G. Ipeirotis","year":"2007","unstructured":"Ipeirotis, P.G., Verykios, V.S., Elmagarmid, A.K.: Duplicate Record Detection: A Survey. IEEE Trans. Knowl. Data Eng.\u00a019(1), 1\u201316 (2007)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"18_CR59","volume-title":"Algorithms for Clustering Data","author":"A.K. Jain","year":"1998","unstructured":"Jain, A.K., Dubes, R.C.: Algorithms for Clustering Data. Prentice-Hall, Englewood Cliffs (1998)"},{"issue":"3","key":"18_CR60","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1145\/331499.331504","volume":"31","author":"A.K. Jain","year":"1999","unstructured":"Jain, A.K., Murty, M.N., Flynn, P.J.: Data Clustering: A Review. ACM Comput. Surv.\u00a031(3), 264\u2013323 (1999)","journal-title":"ACM Comput. Surv."},{"key":"18_CR61","first-page":"420","volume":"84","author":"M.A. Jaro","year":"1989","unstructured":"Jaro, M.A.: Advances in Record Linkage Methodology as Applied to Matching the 1985 Census of Tampa, Florida. Journal of the American Statistical Society\u00a084, 420\u2013424 (1989)","journal-title":"Journal of the American Statistical Society"},{"key":"18_CR62","unstructured":"Kingsbury, N.R., et al.: Record Linkage and Privacy: Issues in Creating New Federal Research and Statistical Information. U.S. General Accounting Office (2001)"},{"issue":"2","key":"18_CR63","first-page":"197","volume":"69","author":"H. Kopcke","year":"2010","unstructured":"Kopcke, H., Rahm, E.: Frameworks for Entity Matching: A Comparison Data and Know. Engineering\u00a069(2), 197\u2013210 (2010)","journal-title":"Engineering"},{"issue":"1","key":"18_CR64","doi-asserted-by":"crossref","first-page":"484","DOI":"10.14778\/1920841.1920904","volume":"3","author":"H. Kopcke","year":"2010","unstructured":"Kopcke, H., Thor, A., Rahm, E.: Evaluation of entity resolution approaches on real-world match problems. Proc. of the VLDB Endowment\u00a03(1), 484\u2013493 (2010)","journal-title":"Proc. of the VLDB Endowment"},{"issue":"4","key":"18_CR65","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1109\/MIC.2010.58","volume":"14","author":"H. Kopcke","year":"2010","unstructured":"Kopcke, H., Thor, A., Rahm, E.: Evaluation of Learning-Based Approaches for Matching Web Data Entities. IEEE Internet Computing\u00a014(4), 23\u201331 (2010)","journal-title":"IEEE Internet Computing"},{"key":"18_CR66","unstructured":"McCallum, A.: MALLET: A Machine Learning for Language Toolkit, http:\/\/mallet.cs.umass.edu"},{"key":"18_CR67","doi-asserted-by":"crossref","unstructured":"Koudas, N., Sevcik, K.C.: Size Separation Spatial Join. In: Proc. of ACM Int. Conf. on Management of Data, pp. 324\u2013335 (1997)","DOI":"10.1145\/253260.253340"},{"key":"18_CR68","doi-asserted-by":"crossref","unstructured":"Lawrence, S., Bollacker, K., Giles, C.L.: Autonomous Citation Matching. In: Proc. of ACM Int. Conf. on Autonomous Agents, pp. 392\u2013393 (1999)","DOI":"10.1145\/301136.301255"},{"issue":"8","key":"18_CR69","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1016\/S0306-4379(01)00041-2","volume":"26","author":"W.L. Low","year":"2001","unstructured":"Low, W.L., Lee, M.L., Ling, T.W.: A Knowledge-Based Approach for Duplicate Elimination in Data Cleaning. Information Systems\u00a026(8), 585\u2013606 (2001)","journal-title":"Information Systems"},{"key":"18_CR70","doi-asserted-by":"crossref","unstructured":"Lwin, T., Nyunt, T.T.S.: An Efficient Duplicate Detection System for XML Documents. In: Proc. of IEEE Int. Conf. on Computer Engineering and Applications, pp. 178\u2013182 (2010)","DOI":"10.1109\/ICCEA.2010.189"},{"key":"18_CR71","unstructured":"McCallum, A., Freitag, D., Pereira, F.: Maximum Entropy Markov Models for Information Extraction and Segmentation. In: Proc. of Int. Conf. on Machine Learning, Standord, California, USA, pp. 591\u2013598 (2000)"},{"key":"18_CR72","doi-asserted-by":"crossref","unstructured":"McCallum, A., Nigam, K., Ungar, L.: Efficient Clustering of High-Dimensional Data Sets with Application to Reference Matching. In: Proc. of ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, Boston, Massachusetts, USA, pp. 169\u2013178 (2000)","DOI":"10.1145\/347090.347123"},{"key":"18_CR73","unstructured":"Menestrina, D., Benjelloun, O., Garcia-Molina, H.: Generic Entity Resolution with Data Confidences. In: Int. VLDB Workshop on Clean Databases, Seoul, Korea (2006)"},{"key":"18_CR74","volume-title":"Machine Learning","author":"T.M. Mitchell","year":"1997","unstructured":"Mitchell, T.M.: Machine Learning. McGraw-Hill, New York (1997)"},{"key":"18_CR75","unstructured":"Monge, A.E., Elkan, C.P.: An Efficient Domain-Independent Algorithm For Detecting Approximately Duplicate Database Records. In: Proc. of SIGMOD Workshop on Research Issues on Data Mining and Knowledge Discovery, Tucson, Arizona, USA, pp. 23\u201329 (1997)"},{"key":"18_CR76","unstructured":"Monge, A.E., Elkan, C.P.: The Field Matching Problem: Algorithms and Applications. In: Proc. of Int. Conf. on Knowledge Discovery and Data Mining, Portland, Oregon, USA, pp. 267\u2013270 (1996)"},{"key":"18_CR77","doi-asserted-by":"crossref","unstructured":"Mukherjee, S., Ramakrishnan, I.V.: Taming the Unstructured: Creating Structured Content from Partially Labeled Schematic Text Sequences. In: Proc. of CoopIS\/DOA\/ODBASE Int. Conf., Agia Napa, Cyprus, pp. 909\u2013926 (2004)","DOI":"10.1007\/978-3-540-30469-2_6"},{"key":"18_CR78","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1002\/sim.4780140511","volume":"14","author":"A.G. Muse","year":"1995","unstructured":"Muse, A.G., Mikl, J., Smith, P.F.: Evaluating the quality of anonymous record linkage using deterministic procedures with the New York State AIDS registry and a hospital discharge file. Statistics in Medicine\u00a014, 499\u2013509 (1995)","journal-title":"Statistics in Medicine"},{"key":"18_CR79","unstructured":"Neiling, M., Jurk, S.: The Object Identification Framework. In: Proc. KDD Workshop on Data Cleaning, Record Linkage, and Object Consolidation, Washington, DC, USA, pp. 37\u201339 (2003)"},{"key":"18_CR80","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1002\/(SICI)1099-1557(199709\/10)6:5<367::AID-PDS299>3.0.CO;2-J","volume":"6","author":"C.I. Neutel","year":"1997","unstructured":"Neutel, C.I.: Privacy Issues in Research Using Record Linkage. Pharmcoepidemiology and Drug Safety\u00a06, 367\u2013369 (1997)","journal-title":"Pharmcoepidemiology and Drug Safety"},{"key":"18_CR81","first-page":"335","volume":"19","author":"H.B. Newcombe","year":"1967","unstructured":"Newcombe, H.B.: Record Linking: The Design of Efficient Systems for Linking Records into Individual and Family Histories. American Journal of Human Genetics\u00a019, 335\u2013359 (1967)","journal-title":"American Journal of Human Genetics"},{"key":"18_CR82","doi-asserted-by":"publisher","first-page":"954","DOI":"10.1126\/science.130.3381.954","volume":"130","author":"H.B. Newcombe","year":"1959","unstructured":"Newcombe, H.B., Kennedy, J.M., Axford, S.J., James, A.P.: Automatic Linkage of Vital Records. Science\u00a0130, 954\u2013959 (1959)","journal-title":"Science"},{"key":"18_CR83","doi-asserted-by":"crossref","unstructured":"Patel, J., DeWitt, D.J.: Partition Based Spatial-Merge Join. In: Proc. of ACM Int. Conf. on Management of Data, pp. 259\u2013270 (1996)","DOI":"10.1145\/233269.233338"},{"key":"18_CR84","unstructured":"Pasula, H., Marthi, B., Milch, B., Russell, S.J., Shpitser, I.: Identity Uncertainty and Citation Matching. In: Proc. of Ann. Conf. on Neural Information Processing Systems, pp. 1401\u20131408 (2002)"},{"key":"18_CR85","doi-asserted-by":"crossref","unstructured":"Sarawagi, S., Bhamidipaty, A.: Interactive Deduplication using Active Learning. In: Proc. of ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, Edmonton, Alberta, Canada, pp. 269\u2013278 (2002)","DOI":"10.1145\/775047.775087"},{"key":"18_CR86","doi-asserted-by":"crossref","unstructured":"Sarawagi, S., Kirpal, A.: Efficient set joins on similarity predicates. In: Proc. of SIGMOD Int. Conf. on Management of Data, Paris, France, pp. 743\u2013754 (2004)","DOI":"10.1145\/1007568.1007652"},{"issue":"6","key":"18_CR87","doi-asserted-by":"publisher","first-page":"973","DOI":"10.1007\/s11390-008-9192-1","volume":"23","author":"H. Shen","year":"2008","unstructured":"Shen, H., Zhang, Y.: Improved Approximate Detection of Duplicates for Data Streams over Sliding Windows. Journal of Computer Science and Technology\u00a023(6), 973\u2013987 (2008)","journal-title":"Journal of Computer Science and Technology"},{"key":"18_CR88","unstructured":"Singla, P., Domingos, P.: Multi-Relational Record Linkage. In: Proc. of ACM Int. Ws. on Multi-Relational Data Mining, pp. 31\u201338 (2004)"},{"issue":"1","key":"18_CR89","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1016\/0022-2836(81)90087-5","volume":"147","author":"S. Smith","year":"1981","unstructured":"Smith, S., Waterman, M.S.: Identification of Common Molecular Subsequences. Journal of Molecular Biology\u00a0147(1), 195\u2013197 (1981)","journal-title":"Journal of Molecular Biology"},{"key":"18_CR90","unstructured":"Statistical Linkage Key Working Group. Statistical Data Linkage in Community Services Data Collections (2002)"},{"key":"18_CR91","doi-asserted-by":"crossref","unstructured":"Tejada, S., Knoblock, C.A., Minton, S.: Learning Domain-Independent String Transformation Weights for High Accuracy Object Identification. In: Proc. of ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, Edmonton, Alberta, Canada, pp. 350\u2013359 (2002)","DOI":"10.1145\/775047.775099"},{"key":"18_CR92","doi-asserted-by":"publisher","first-page":"1321","DOI":"10.2307\/2285887","volume":"63","author":"J.B. Tepping","year":"1968","unstructured":"Tepping, J.B.: A Model for Optimum Linkage of Records. Journal of the American Statistical Association\u00a063, 1321\u20131332 (1968)","journal-title":"Journal of the American Statistical Association"},{"issue":"1-4","key":"18_CR93","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1016\/S0020-0255(00)00013-X","volume":"126","author":"V.S. Verykios","year":"2000","unstructured":"Verykios, V.S., Elmagarmid, A.K., Houstis, E.N.: Automating the approximate record-matching process. Inf. Sci.\u00a0126(1-4), 83\u201398 (2000)","journal-title":"Inf. Sci."},{"key":"18_CR94","unstructured":"Weber, R., Schek, H.J., Blott, S.: A Quantitative Analsysis and Performance Study for Similarity Search in High-Dimensional Spaces. In: Proc. of Int. Conf. on Very Large Databases, New York City, USA, pp. 194\u2013205 (1998)"},{"key":"18_CR95","doi-asserted-by":"crossref","unstructured":"Weis, M., Naumann, N.: Detecting Duplicates in Complex XML Data. In: Proc. of IEEE Int. Conf. on Data Engineering, p. 109 (2006)","DOI":"10.1109\/ICDE.2006.49"},{"key":"18_CR96","unstructured":"Weis, M., Naumann, N.: Space and Time Scalability of Duplicate Detection in Graph Data. Tech. Rep. 25, Hasso-Plattner Institut, Potsdam, Germany (2007)"},{"key":"18_CR97","unstructured":"Winkler, W.E.: String Comparator Metrics and Enhanced Decision Rules in the Fellegi-Sunter Model of Record Linkage. In: Proc. Section on Survey Research Methods, American Statistical Association, pp. 354\u2013359 (1990)"},{"key":"18_CR98","unstructured":"Winkler, W.E.: Overview of Record Linkage and Current Research Directions. Technical Report. Statistical Research Division, U.S. Census Bureau (1999)"},{"key":"18_CR99","unstructured":"Winkler, W.E.: Methods for Record Linkage and Bayesian Networks. Tech. Rep. RRS2002\/05, U.S. Bureau of the Census, Washington, D.C., USA (2002)"},{"issue":"4","key":"18_CR100","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1109\/TKDE.2009.68","volume":"22","author":"Y. Zhang","year":"2010","unstructured":"Zhang, Y., Lin, X., Yuan, Y., Kitsuregawa, M., Zhou, X., Yu, J.X.: Duplicate-insensitive Order Statistics Computation over Data Streams. IEEE Transanctions on Knowledge and Data Engineering\u00a022(4), 493\u2013507 (2010)","journal-title":"IEEE Transanctions on Knowledge and Data Engineering"}],"container-title":["Studies in Computational Intelligence","Learning Structure and Schemas from Documents"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-22913-8_18.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T23:41:20Z","timestamp":1741736480000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-22913-8_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011]]},"ISBN":["9783642229121","9783642229138"],"references-count":100,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-22913-8_18","relation":{},"ISSN":["1860-949X","1860-9503"],"issn-type":[{"value":"1860-949X","type":"print"},{"value":"1860-9503","type":"electronic"}],"subject":[],"published":{"date-parts":[[2011]]}}}