{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T07:29:15Z","timestamp":1791444555121,"version":"4.3.3"},"publisher-location":"Berlin, Heidelberg","reference-count":48,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642140099","type":"print"},{"value":"9783642140105","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-3-642-14010-5_8","type":"book-chapter","created":{"date-parts":[[2010,9,3]],"date-time":"2010-09-03T09:22:11Z","timestamp":1283505731000},"page":"193-224","source":"Crossref","is-referenced-by-count":9,"title":["An Overview of XML Duplicate Detection Algorithms"],"prefix":"10.1007","author":[{"given":"P\u00e1vel","family":"Calado","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Melanie","family":"Herschel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu\u00eds","family":"Leit\u00e3o","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Ananthakrishna, R., Chaudhuri, S., Ganti, V.: Eliminating fuzzy duplicates in data warehouses. In: Conference on Very Large Databases (VLDB), Hong Kong, China, pp. 586\u2013597 (2002)","DOI":"10.1016\/B978-155860869-6\/50058-5"},{"key":"8_CR2","volume-title":"Modern information retrieval","author":"R.A. Baeza-Yates","year":"1999","unstructured":"Baeza-Yates, R.A., Ribeiro-Neto, B.: Modern information retrieval. Addison-Wesley Longman Publishing Co., Inc., Boston (1999)"},{"key":"8_CR3","volume-title":"Data quality - concepts, methodologies and techniques","author":"C. Batini","year":"2006","unstructured":"Batini, C., Scannapieco, M.: Data quality - concepts, methodologies and techniques. Springer, Berlin (2006)"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Bhattacharya, I., Getoor, L.: Relational clustering for multi-type entity resolution. In: KDD Workshop on Multi-Relational Data Mining, MRDM (2005)","DOI":"10.1145\/1090193.1090195"},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"Bhattacharya, I., Getoor, L.: A latent dirichlet model for unsupervised entity resolution. In: Conference on Data Mining (SDM), Bethesda, MD (2006)","DOI":"10.1137\/1.9781611972764.5"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Bhattacharya, I., Getoor, L.: Collective entity resolution in relational data. ACM Transactions on Knowledge Discovery from Data 1(1) (2007)","DOI":"10.1145\/1217299.1217304"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Bilenko, M., Mooney, R.J.: Adaptive duplicate detection using learnable string similarity measures. In: Conference on Knowledge Discovery and Data Mining (KDD), Washington, DC, pp. 39\u201348 (2003)","DOI":"10.1145\/956750.956759"},{"issue":"1\u20133","key":"8_CR8","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1016\/j.tcs.2004.12.030","volume":"337","author":"P. Bille","year":"2005","unstructured":"Bille, P.: A survey on tree edit distance and related problems. Theoretical Computer Science\u00a0337(1\u20133), 217\u2013239 (2005)","journal-title":"Theoretical Computer Science"},{"issue":"1","key":"8_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1456650.1456651","volume":"41","author":"J. Bleiholder","year":"2008","unstructured":"Bleiholder, J., Naumann, F.: Data fusion. ACM Comput. Surv.\u00a041(1), 1\u201341 (2008), http:\/\/doi.acm.org\/10.1145\/1456650.1456651","journal-title":"ACM Comput. Surv."},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Carvalho, J.C.P., da Silva, A.S.: Finding similar identities among objects from multiple web sources. In: CIKM Workshop on Web Information and Data Management (WIDM), New Orleans, Louisiana, USA, pp. 90\u201393 (2003)","DOI":"10.1145\/956699.956719"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Chaudhuri, S., Ganjam, K., Ganti, V., Motwani, R.: Robust and efficient fuzzy match for online data cleaning. In: Conference on the Management of Data (SIGMOD), San Diego, CA, pp. 313\u2013324 (2003)","DOI":"10.1145\/872757.872796"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Chaudhuri, S., Ganti, V., Motwani, R.: Robust identification of fuzzy duplicates. In: International Conference on Data Engineering (ICDE), Tokyo, Japan, pp. 865\u2013876 (2005)","DOI":"10.1109\/ICDE.2005.125"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Chen, Z., Kalashnikov, D.V., Mehrotra, S.: Exploiting relationships for object consolidation. In: SIGMOD Workshop on Information Quality in Information Systems (IQIS), Baltimore, MD (2005)","DOI":"10.1145\/1077501.1077512"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Cohen, W.W., Richman, J.: Learning to match and cluster large high-dimensional data sets for data integration. In: Conference on Knowledge Discovery and Data Mining (KDD), Edmonton, Alberta, Canada, pp. 475\u2013480 (2002)","DOI":"10.1007\/3-540-47887-6"},{"issue":"5","key":"8_CR15","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1109\/MIS.2003.1234770","volume":"18","author":"A. Doan","year":"2003","unstructured":"Doan, A., Lu, Y., Lee, Y., Han, J.: Profile-based object matching for information integration. IEEE Intelligent Systems\u00a018(5), 54\u201359 (2003)","journal-title":"IEEE Intelligent Systems"},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Dong, X., Halevy, A., Madhavan, J.: Reference reconciliation in complex information spaces. In: Conference on the Management of Data (SIGMOD), Baltimore, MD, pp. 85\u201396 (2005)","DOI":"10.1145\/1066157.1066168"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Elfeky, M.G., Elmagarmid, A.K., Verykios, V.S.: Tailor: A record linkage tool box. In: International Conference on Data Engineering (ICDE), San Jose, CA, pp. 17\u201328 (2002)","DOI":"10.1109\/ICDE.2002.994694"},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"Elmagarmid, A.K., Ipeirotis, P.G., Verykios, V.S.: Duplicate record detection: A survey. IEEE Trans. Knowl. Data Eng. 19(1) (2007)","DOI":"10.1109\/TKDE.2007.250581"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Fellegi, I.P., Sunter, A.B.: A theory for record linkage. Journal of the American Statistical Association (1969)","DOI":"10.1080\/01621459.1969.10501049"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Guha, S., Jagadish, H.V., Koudas, N., Srivastava, D., Yu, T.: Approximate XML joins. In: Conference on the Management of Data (SIGMOD), Madison, WI (2002)","DOI":"10.1145\/564691.564725"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Hern\u00e1ndez, M.A., Stolfo, S.J.: The merge\/purge problem for large databases. In: Conference on the Management of Data (SIGMOD), San Jose, CA, pp. 127\u2013138 (1995)","DOI":"10.1145\/568271.223807"},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"Herschel, M., Naumann, F.: Scaling up duplicate detection in graph data. In: Conference on Information and Knowledge Management (CIKM), pp. 1325\u20131326 (2008)","DOI":"10.1145\/1458082.1458259"},{"key":"8_CR23","unstructured":"Jin, L., Li, C., Mehrotra, S.: Efficient record linkage in large data sets. In: Conference on Database Systems for Advanced Applications (DASFAA), Kyoto, Japan (2003)"},{"issue":"2","key":"8_CR24","doi-asserted-by":"publisher","first-page":"716","DOI":"10.1145\/1138394.1138401","volume":"31","author":"D.V. Kalashnikov","year":"2006","unstructured":"Kalashnikov, D.V., Mehrotra, S.: Domain-independent data cleaning via analysis of entity-relationship graph. ACM Transactions on Database Systems (TODS)\u00a031(2), 716\u2013767 (2006)","journal-title":"ACM Transactions on Database Systems (TODS)"},{"issue":"1\u20132","key":"8_CR25","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"H.W. Kuhn","year":"1955","unstructured":"Kuhn, H.W.: The hungarian method for the assignment problem. Naval Research Logistics Quarterly\u00a02(1\u20132), 83\u201397 (1955)","journal-title":"Naval Research Logistics Quarterly"},{"key":"8_CR26","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1007\/11890591_5","volume":"4244","author":"P. Lehti","year":"2006","unstructured":"Lehti, P., Fankhauser, P.: Unsupervised duplicate detection using sample non-duplicates. Journal on Data Semantics VII\u00a04244, 136\u2013164 (2006)","journal-title":"Journal on Data Semantics VII"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Leit\u00e3o, L., Calado, P., Weis, M.: Structure-based inference of XML similarity for fuzzy duplicate detection. In: Conference on Information and Knowledge Management (CIKM), pp. 293\u2013302 (2007)","DOI":"10.1145\/1321440.1321483"},{"key":"8_CR28","first-page":"707","volume":"10","author":"V. Levenshtein","year":"1966","unstructured":"Levenshtein, V.: Binary Codes Capable of Correcting Deletions, Insertions and Reversals. Soviet Physics Doklady\u00a010, 707 (1966)","journal-title":"Soviet Physics Doklady"},{"key":"8_CR29","doi-asserted-by":"crossref","unstructured":"Lim, E.P., Srivastava, J., Prabhakar, S., Richardson, J.: Entity identification in database integration. In: International Conference on Data Engineering (ICDE), Vienna, Austria, pp. 294\u2013301 (1993)","DOI":"10.1109\/ICDE.1993.344053"},{"key":"8_CR30","unstructured":"McCallum, A., Wellner, B.: Object consolidation by graph partitioning with a conditionally-trained distance metric. In: KDD Workshop on Data Cleaning, Record Linkage and Object Consolidation, Washington, DC (2003)"},{"key":"8_CR31","unstructured":"Milano, D., Scannapieco, M., Catarci, T.: Structure aware XML object identification. In: VLDB Workshop on Clean Databases (CleanDB), Seoul, Korea (2006)"},{"key":"8_CR32","doi-asserted-by":"crossref","unstructured":"Minkov, E., Cohen, W.W., Ng, A.Y.: Contextual search and name disambiguation in email using graphs. In: Conference on Research and Development in Information Retrieval (SIGIR), Seattle, Washington, USA, pp. 27\u201334 (2006)","DOI":"10.1145\/1148170.1148179"},{"key":"8_CR33","unstructured":"Monge, A.E., Elkan, C.P.: An efficient domain-independent algorithm for detecting approximately duplicate database records. In: SIGMOD Workshop on Research Issues in Data Mining and Knowledge Discovery (DMKD), Tucson, AZ (1997)"},{"issue":"3381","key":"8_CR34","doi-asserted-by":"publisher","first-page":"954","DOI":"10.1126\/science.130.3381.954","volume":"130","author":"H. Newcombe","year":"1959","unstructured":"Newcombe, H., Kennedy, J., Axford, S., James, A.: Automatic linkage of vital records. Science\u00a0130(3381), 954\u2013959 (1959)","journal-title":"Science"},{"key":"8_CR35","volume-title":"Probabilistic Reasoning in Intelligent Systems: Networks of plausible inference","author":"J. Pearl","year":"1988","unstructured":"Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of plausible inference, 2nd edn. Morgan Kaufmann Publishers, San Francisco (1988)","edition":"2"},{"key":"8_CR36","doi-asserted-by":"crossref","unstructured":"Puhlmann, S., Weis, M., Naumann, F.: XML duplicate detection using sorted neigborhoods. In: Conference on Extending Database Technology (EDBT), Munich, Germany, pp. 773\u2013791 (2006)","DOI":"10.1007\/11687238_46"},{"issue":"4","key":"8_CR37","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1007\/s007780100057","volume":"10","author":"E. Rahm","year":"2001","unstructured":"Rahm, E., Bernstein, P.A.: A survey of approaches to automatic schema matching. VLDB Journal\u00a010(4), 334\u2013350 (2001)","journal-title":"VLDB Journal"},{"key":"8_CR38","first-page":"3","volume":"23","author":"E. Rahm","year":"2000","unstructured":"Rahm, E., Do, H.H.: Data cleaning: Problems and current approaches. IEEE Data Engineering Bulletin\u00a023, 3\u201313 (2000)","journal-title":"IEEE Data Engineering Bulletin"},{"key":"8_CR39","doi-asserted-by":"crossref","unstructured":"Sarawagi, S., Bhamidipaty, A.: Interactive deduplication using active learning. In: Conference on Knowledge Discovery and Data Mining (KDD), Edmonton, Alberta, pp. 269\u2013278 (2002)","DOI":"10.1145\/775047.775087"},{"key":"8_CR40","unstructured":"Singla, P., Domingos, P.: Multi-relational record linkage. In: KDD Workshop on Multi-Relational Data Mining (MRDM), Seattle, WA (2004)"},{"key":"8_CR41","doi-asserted-by":"crossref","unstructured":"Singla, P., Domingos, P.: Object identification with attribute-mediated dependences. In: Conference on Principals and Practice of Knowledge Discovery in Databases (PKDD), Porto, Portugal, pp. 297\u2013308 (2005)","DOI":"10.1007\/11564126_31"},{"key":"8_CR42","unstructured":"Weis, M.: Duplicate Detection in XML Data. WiKu-Verlag Verlag fuer Wissenschaft und Kultur (2008)"},{"key":"8_CR43","doi-asserted-by":"crossref","unstructured":"Weis, M., Naumann, F.: Duplicate detection in XML. In: SIGMOD Workshop on Information Quality in Information Systems (IQIS), Paris, France, pp. 10\u201319 (2004)","DOI":"10.1145\/1012453.1012456"},{"key":"8_CR44","doi-asserted-by":"crossref","unstructured":"Weis, M., Naumann, F.: Dogmatix tracks down duplicates in XML. In: Conference on the Management of Data (SIGMOD), Baltimore, MD, pp. 431\u2013442 (2005)","DOI":"10.1145\/1066157.1066207"},{"key":"8_CR45","doi-asserted-by":"crossref","unstructured":"Weis, M., Naumann, F.: Detecting duplicates in complex XML data. In: International Conference on Data Engineering (ICDE), Atlanta, GA (2006)","DOI":"10.1109\/ICDE.2006.49"},{"key":"8_CR46","doi-asserted-by":"crossref","unstructured":"Weis, M., Naumann, F., Jehle, U., Lufter, J., Schuster, H.: Industry-scale duplicate detection. In: Proceedings of the VLDB Endowment (PVLDB), vol.\u00a01(2), pp. 1253\u20131264 (2008)","DOI":"10.14778\/1454159.1454165"},{"key":"8_CR47","volume-title":"Conference on the Management of Data (SIGMOD)","author":"S.E. Whang","year":"2009","unstructured":"Whang, S.E., Menestrina, D., Koutrika, G., Tin Theobald, M., Garcia-Molina, H.: Entity resolution with iterative blocking. In: Conference on the Management of Data (SIGMOD). Providence, Rhode Island (2009)"},{"key":"8_CR48","unstructured":"Yin, X., Han, J., Yu, P.S.: LinkClus: Efficient clustering via heterogeneous semantic links. In: Conference on Very Large Databases (VLDB), Seoul, Korea, pp. 427\u2013438 (2006)"}],"container-title":["Studies in Fuzziness and Soft Computing","Soft Computing in XML Data Management"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-14010-5_8.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,25]],"date-time":"2025-02-25T13:57:01Z","timestamp":1740491821000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-14010-5_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642140099","9783642140105"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-14010-5_8","relation":{},"ISSN":["1434-9922","1860-0808"],"issn-type":[{"value":"1434-9922","type":"print"},{"value":"1860-0808","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010]]}}}