{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,12]],"date-time":"2025-09-12T18:01:02Z","timestamp":1757700062475,"version":"3.37.3"},"publisher-location":"Berlin, Heidelberg","reference-count":19,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642142451"},{"type":"electronic","value":"9783642142468"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-3-642-14246-8_69","type":"book-chapter","created":{"date-parts":[[2010,7,6]],"date-time":"2010-07-06T14:09:26Z","timestamp":1278425366000},"page":"729-741","source":"Crossref","is-referenced-by-count":1,"title":["A Multilevel and Domain-Independent Duplicate Detection Model for Scientific Database"],"prefix":"10.1007","author":[{"given":"Jie","family":"Song","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yubin","family":"Bao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ge","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"issue":"4","key":"69_CR1","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1145\/1107499.1107503","volume":"34","author":"J. Gray","year":"2005","unstructured":"Gray, J., Liu, D.T., Nieto-Santisteban, M.A., Szalay, A., et al.: Scientific Data Management in The Coming Decade. SIGMOD Record.\u00a034(4), 34\u201341 (2005)","journal-title":"SIGMOD Record."},{"issue":"3","key":"69_CR2","first-page":"1","volume":"23","author":"E. Rahm","year":"2000","unstructured":"Rahm, E., Do, H.H.: Data Cleaning: Problem and Current Approaches. IEEE Data Engineering Bulletin\u00a023(3), 1 (2000)","journal-title":"IEEE Data Engineering Bulletin"},{"key":"69_CR3","unstructured":"Galhardas, H., Florescu, D., Shasha, D., Simon, E., Saita, C.: Declarative Data Cleaning: Language, Model, and Algorithms. In: Proc. of International Conf. on Very Large Databases, pp. 371\u2013380 (2001)"},{"key":"69_CR4","doi-asserted-by":"crossref","unstructured":"Hernandez, M., Stolfo, S.: The Merge\/Purge Problem for Large Databases. In: Proc. of the ACM SIGMOD, pp. 127\u2013138 (May 1995)","DOI":"10.1145\/223784.223807"},{"key":"69_CR5","doi-asserted-by":"crossref","first-page":"1183","DOI":"10.1080\/01621459.1969.10501049","volume":"64","author":"I.P. Felligi","year":"1969","unstructured":"Felligi, I.P., Sunter, A.B.: A Theory for Record Linkage. Journal of the American Statistical Society\u00a064, 1183\u20131210 (1969)","journal-title":"Journal of the American Statistical Society"},{"key":"69_CR6","doi-asserted-by":"crossref","unstructured":"Bhattacharya, I., Getoor, L.: Relational Clustering for Multi-type Entity Resolution. In: Proc. of Workshop on Multi-Relational Data Mining, MRDM (2005)","DOI":"10.1145\/1090193.1090195"},{"key":"69_CR7","doi-asserted-by":"crossref","unstructured":"Dong, X., Halevy, A., Madhavan, J.: Reference Reconciliation in Complex Information Spaces. In: Proc. of SIGMOD, pp. 85\u201396 (2005)","DOI":"10.1145\/1066157.1066168"},{"key":"69_CR8","unstructured":"Monge, A., Elkan, C.: An Efficient Domain Independent Algorithm for Detecting Approximately Duplicate Database Records. In: Proc. of the SIGMOD Workshop on Data Mining and Knowledge Discovery (May 1997)"},{"key":"69_CR9","unstructured":"Garcia, E.: An Information Retrieval Tutorial on Cosine Similarity Measures, Dot Products and Term Weight Calculations, http:\/\/www.miislita.com\/information-retrieval-tutorial\/cosine-similarity-tutorial.html#Cosim"},{"issue":"1","key":"69_CR10","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1016\/S0306-4573(97)00067-8","volume":"34","author":"R. Rousseau","year":"1998","unstructured":"Rousseau, R.: Jaccard Similarity Leads to the Marczewski-Steinhaus Topology for Information Retrieval. Inf. Process. Manage. (IPM)\u00a034(1), 87\u201394 (1998)","journal-title":"Inf. Process. Manage. (IPM)"},{"key":"69_CR11","unstructured":"Black, P.E. (ed.): Euclidean Distance, in Dictionary of Algorithms and Data Structures, U.S. National Institute of Standards and Technology, http:\/\/www.itl.nist.gov\/div897\/sqg\/dads\/HTML\/euclidndstnc.html"},{"key":"69_CR12","unstructured":"Mahalanobis, P.C.: On the generalised distance in statistics. Proceedings of the National Institute of Sciences of India 2 (1), 49\u201355"},{"key":"69_CR13","doi-asserted-by":"crossref","unstructured":"Xue, Z.-a., Cen, F., Wei, L.-p.: A Weighting Fuzzy Clustering Algorithm Based on Euclidean Distance. In: FSKD 2008, pp. 172\u2013175 (2008)","DOI":"10.1109\/FSKD.2008.98"},{"key":"69_CR14","doi-asserted-by":"crossref","unstructured":"Jin, L., Li, C., Mehrotra, S.: Efficient Record Linkage in Large Data Sets. In: Proc. of International Conf. on Database Systems for Advanced Applications, p. 137 (2003)","DOI":"10.1109\/DASFAA.2003.1192377"},{"key":"69_CR15","doi-asserted-by":"crossref","unstructured":"Lim, E.P., Srivastava, J., Prabhakar, S., Richardson, J.: Entity Identification in Database Integration. In: Proc. of International Conf. on Data Engineering, pp. 294\u2013301 (April 1993)","DOI":"10.1109\/ICDE.1993.344053"},{"key":"69_CR16","unstructured":"Weis, M.: Fuzzy Duplicate Detection on XML. In: VLDB PhD Workshop (2005)"},{"key":"69_CR17","doi-asserted-by":"crossref","unstructured":"Weis, M., Naumann, F.: Duplicate Detection in XML. In: Proc. of the ACM SIGMOD Workshop on Information Quality in Information Systems, pp. 10\u201319 (2004)","DOI":"10.1145\/1012453.1012456"},{"key":"69_CR18","doi-asserted-by":"crossref","unstructured":"Ananthakrishna, R., Chaudhuri, S., Ganti, V.: Eliminating Fuzzy Duplicates in Data Warehouses. In: Proc. of VLDB, pp. 586\u2013597 (2002)","DOI":"10.1016\/B978-155860869-6\/50058-5"},{"key":"69_CR19","doi-asserted-by":"crossref","unstructured":"Bhattacharya, I., Getoor, L.: Relational Clustering for Multi-type Entity Resolution. In: Proc. of Workshop on Multi-Relational Data Mining, MRDM (2005)","DOI":"10.1145\/1090193.1090195"}],"container-title":["Lecture Notes in Computer Science","Web-Age Information Management"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-14246-8_69.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,22]],"date-time":"2025-02-22T17:20:35Z","timestamp":1740244835000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-14246-8_69"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642142451","9783642142468"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-14246-8_69","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2010]]}}}