{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T18:57:57Z","timestamp":1725562677869},"publisher-location":"Berlin, Heidelberg","reference-count":17,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642145889"},{"type":"electronic","value":"9783642145896"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-3-642-14589-6_14","type":"book-chapter","created":{"date-parts":[[2010,8,16]],"date-time":"2010-08-16T14:38:13Z","timestamp":1281969493000},"page":"130-142","source":"Crossref","is-referenced-by-count":0,"title":["On Memory and I\/O Efficient Duplication Detection for Multiple Self-clean Data Sources"],"prefix":"10.1007","author":[{"given":"Ji","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanfeng","family":"Shu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hua","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Ananthakrishna, R., Chaudhuri, S., Ganti, V.: Eliminating Fuzzy Duplicates in Data Warehouses. In: Proceedings of the 28th International Conference on Very Large Databases (VLDB 2002), Hong Kong, China, pp. 586\u2013597 (2002)","DOI":"10.1016\/B978-155860869-6\/50058-5"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Andritsos, P., Miller, R.J., Tsaparas, P.: Information-Theoretic Tools for Mining Database Structure from Large Data Sets. In: Proceedings of ACM SIGMOD 2004, Paris, France, pp. 731\u2013742 (2004)","DOI":"10.1145\/1007568.1007650"},{"key":"14_CR3","unstructured":"Bilenko, M., Mooney, R.J.: On Evaluation and Training-Set Construction for Duplicate Detection. In: Proceedings of the KDD 2003 Workshop on Data Cleaning, Record Linkage, and Object Consolidation, Washington, DC, August 2003, pp. 7\u201312 (2003)"},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Chaudhuri, S., Ganjam, K., Ganti, V., Motwani, R.: Robust and Efficient Fuzzy Match for Online Data Cleaning. In: Proceedings of ACM SIGMOD 2003, San Diego, USA, pp. 313\u2013324 (2003)","DOI":"10.1145\/872757.872796"},{"key":"14_CR5","volume-title":"Improving Data Warehouse and Business Information Quality","author":"L.P. English","year":"1999","unstructured":"English, L.P.: Improving Data Warehouse and Business Information Quality. J. Wiley and Sons, New York (1999)"},{"key":"14_CR6","unstructured":"Hernandez, M.: A Generation of Band Joins and the Merge\/Purge Problem. Technical Report CUCS-005-1995, Columbia University (February 1995)"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Hernandez, M.A., Stolfo, S.J.: The Merge\/Purge Problem for Large Databases. In: Proceedings of the 1995 ACM-SIGMOD International Conference on Management of Data, pp. 127\u2013138 (1995)","DOI":"10.1145\/223784.223807"},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Gravano, L., Ipeirotis, P.G., Koudas, N., Srivastava, D.: Text Joins for Data Cleansing and Integration in an RDBMS. In: Proceedings of ICDE 2003, Bangalore, India, pp. 729\u2013731 (2003)","DOI":"10.1109\/ICDE.2003.1260850"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Low, W.L., Lee, M.L., Ling, T.W.: A Knowledge-Based Framework for Duplicates Elimination. Information Systems: Special Issue on Data Extraction, Cleaning and Reconciliation\u00a026(8) (2001)","DOI":"10.1016\/S0306-4379(01)00041-2"},{"key":"14_CR10","unstructured":"Monge, A.E., Elkan, C.P.: An Efficient Domain-independent Algorithm for detecting Approximately Duplicate Database Records. In: Proceedings of SIDGMOD Workshop on Research issues and Data Mining and Knowledge Discovery (1997)"},{"key":"14_CR11","unstructured":"Monge, A.E., Elkan, C.P.: The Field Matching Problem: Algorithms and Application. In: Proceedings of International Conference on Knowledge Discovery and Data Mining (SIGKDD 1996), pp. 267\u2013270 (1996)"},{"key":"14_CR12","series-title":"Lecture Notes in Computer Science","first-page":"484","volume-title":"Database and Expert Systems Applications","author":"Z. Li","year":"2002","unstructured":"Li, Z., Sung, S.Y., Sun, P., Ling, T.W.: A New Efficient Data Cleansing Method. In: Hameurlain, A., Cicchetti, R., Traunm\u00fcller, R. (eds.) DEXA 2002. LNCS, vol.\u00a02453, p. 484. Springer, Heidelberg (2002)"},{"key":"14_CR13","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1016\/0022-2836(81)90087-5","volume":"147","author":"T.F. Smith","year":"1981","unstructured":"Smith, T.F., Waterman, M.S.: Identification of Common Molecular Subsequences. Journal of Molecular Biology\u00a0147, 195\u2013197 (1981)","journal-title":"Journal of Molecular Biology"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Sung, S.Y., Li, Z., Peng, S.: A Fast Filtering Scheme for Large Database Cleansing. In: Proceedings of Conference on Information and Knowledge Management (CIKM 2002), pp. 76\u201383 (2002)","DOI":"10.1145\/584792.584808"},{"key":"14_CR15","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1007\/s007990100044","volume":"3","author":"Z. Tian","year":"2002","unstructured":"Tian, Z., Lu, H., Ji, W., Zhou, A., Tian, Z.: An N-gram-based Approach for Detecting Approximately Duplicate Database Records. International Journal of Digital Library\u00a03, 325\u2013331 (2002)","journal-title":"International Journal of Digital Library"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Weis, M., Naumann, F.: Detecting Duplicate Objects in XML Documents. In: Proceedings of IQIS 2004, Paris, France, pp. 10\u201319 (2004)","DOI":"10.1145\/1012453.1012456"},{"key":"14_CR17","series-title":"Lecture Notes in Computer Science","first-page":"486","volume-title":"Database and Expert Systems Applications","author":"J. Zhang","year":"2004","unstructured":"Zhang, J., Ling, T.W., Bruckner, R.M., Liu, H.: PC-Filter: A Robust Filtering Technique for Duplicate Record Detection in Large Databases. In: Galindo, F., Takizawa, M., Traunm\u00fcller, R. (eds.) DEXA 2004. LNCS, vol.\u00a03180, pp. 486\u2013496. Springer, Heidelberg (2004)"}],"container-title":["Lecture Notes in Computer Science","Database Systems for Advanced Applications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-14589-6_14.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,24]],"date-time":"2020-11-24T02:55:01Z","timestamp":1606186501000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-14589-6_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642145889","9783642145896"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-14589-6_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2010]]}}}