{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T11:27:31Z","timestamp":1783078051460,"version":"3.54.6"},"publisher-location":"Berlin, Heidelberg","reference-count":24,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783540269724","type":"print"},{"value":"9783540316930","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2005]]},"DOI":"10.1007\/11508069_15","type":"book-chapter","created":{"date-parts":[[2010,9,26]],"date-time":"2010-09-26T14:30:58Z","timestamp":1285511458000},"page":"109-116","source":"Crossref","is-referenced-by-count":33,"title":["Probabilistic Data Generation for Deduplication and Data Linkage"],"prefix":"10.1007","author":[{"given":"Peter","family":"Christen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"Bertolazzi, P., De Santis, L., Scannapieco, M.: Automated record matching in cooperative information systems. In: Proceedings of the international workshop on data quality in cooperative information systems, Siena, Italy (January 2003)","DOI":"10.1007\/978-3-540-39964-3_23"},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Bilenko, M., Mooney, R.J.: Adaptive duplicate detection using learnable string similarity measures. In: Proceedings of the 9th ACM SIGKDD conference, Washington, DC (August 2003)","DOI":"10.1145\/956750.956759"},{"key":"15_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)"},{"key":"15_CR4","unstructured":"Blake, C.L., Merz, C.J.: UCI Repository of machine learning databases. University of California, Irvine, Dept. of Information and Computer Sciences, http:\/\/www.ics.uci.edu\/~mlearn\/MLRepository.html"},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Chaudhuri, S., Ganti, V., Motwani, R.: Robust identification of fuzzy duplicates. In: Proceedings of the 21st international conference on data engineering, Tokyo (April 2005)","DOI":"10.1109\/ICDE.2005.125"},{"key":"15_CR6","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"638","DOI":"10.1007\/978-3-540-24775-3_75","volume-title":"Advances in Knowledge Discovery and Data Mining","author":"P. Christen","year":"2004","unstructured":"Christen, P., Churches, T., Hegland, M.: A parallel open source data linkage system. In: Dai, H., Srikant, R., Zhang, C. (eds.) PAKDD 2004. LNCS (LNAI), vol.\u00a03056, pp. 638\u2013647. Springer, Heidelberg (2004)"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Cohen, W.W., Richman, J.: Learning to match and cluster large highdimensional data sets for data integration. In: Proceedings of the 8th ACM SIGKDD conference, Edmonton (July 2002)","DOI":"10.1145\/775107.775116"},{"key":"15_CR8","unstructured":"Cohen, W.W., Ravikumar, P., Fienberg, S.E.: A comparison of string distance metrics for name-matching tasks. In: Proceedings of IJCAI 2003 workshop on information integration on the Web (IIWeb 2003), Acapulco, August 2003, pp. 73\u201378 (2003)"},{"issue":"3","key":"15_CR9","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1145\/363958.363994","volume":"7","author":"F. Damerau","year":"1964","unstructured":"Damerau, F.: A technique for computer detection and correction of spelling errors. Communications of the ACM\u00a07(3), 171\u2013176 (1964)","journal-title":"Communications of the ACM"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Elfeky, M.G., Verykios, V.S., Elmagarmid, A.K.: TAILOR: A record linkage toolbox. In: Proceedings of the ICDE 2002, San Jose, USA (March 2002)","DOI":"10.1109\/ICDE.2002.994694"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Fellegi, I., Sunter, A.: A theory for record linkage. Journal of the American Statistical Society (December 1969)","DOI":"10.2307\/2286061"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Gu, L., Baxter, R.: Adaptive filtering for efficient record linkage. In: SIAM international conference on data mining, Orlando, Florida (April 2004)","DOI":"10.1137\/1.9781611972740.50"},{"issue":"4","key":"15_CR13","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1145\/356827.356830","volume":"12","author":"P.A.V. Hall","year":"1980","unstructured":"Hall, P.A.V., Dowling, G.R.: Approximate string matching. ACM computing surveys\u00a012(4), 381\u2013402 (1980)","journal-title":"ACM computing surveys"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Hernandez, M.A., Stolfo, S.J.: The merge\/purge problem for large databases. In: Proceedings of the ACM SIGMOD conference (May 1995)","DOI":"10.1145\/223784.223807"},{"issue":"4","key":"15_CR15","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1145\/146370.146380","volume":"24","author":"K. Kukich","year":"1992","unstructured":"Kukich, K.: Techniques for automatically correcting words in text. ACM computing surveys\u00a024(4), 377\u2013439 (1992)","journal-title":"ACM computing surveys"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"McCallum, A., Nigam, K., Ungar, L.H.: Efficient clustering of high-dimensional data sets with application to reference matching. In: Proceedings of the 6th ACM SIGKDD conference, Boston, August 2000, pp. 169\u2013178 (2000)","DOI":"10.1145\/347090.347123"},{"key":"15_CR17","unstructured":"Nahm, U.Y., Bilenko, M., Mooney, R.J.: Two approaches to handling noisy variation in text mining. In: Proceedings of the ICML 2002 workshop on text learning (TextML 2002), Sydney, Australia, July 2002, pp. 18\u201327 (2002)"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Centre for Epidemiology and Research, NSW Department of Health. New South Wales Mothers and Babies, NSW Public Health Bull 2002; 13(S-4) (2001)","DOI":"10.1071\/NB02S35"},{"issue":"4","key":"15_CR19","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1145\/358027.358048","volume":"27","author":"J.J. Pollock","year":"1984","unstructured":"Pollock, J.J., Zamora, A.: Automatic spelling correction in scientific and scholarly text. Communications of the ACM\u00a027(4), 358\u2013368 (1984)","journal-title":"Communications of the ACM"},{"key":"15_CR20","unstructured":"Ravikumar, P., Cohen, W.W.: A hierarchical graphical model for record linkage. In: Proceedings of the 20th conference on uncertainty in artificial intelligence, Banff, Canada (July 2004)"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Sarawagi, S., Bhamidipaty, A.: Interactive deduplication using active learning. In: Proceedings of the 8th ACM SIGKDD conference, Edmonton (July 2002)","DOI":"10.1145\/775047.775087"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Tejada, S., Knoblock, C.A., Minton, S.: Learning domain-independent string transformation weights for high accuracy object identification. In: Proceedings of the 8th ACM SIGKDD conference, Edmonton (July 2002)","DOI":"10.1145\/775047.775099"},{"key":"15_CR23","unstructured":"Yancey, W.E.: An adaptive string comparator for record linkage RR 2004-02, US Bureau of the Census (February 2004)"},{"key":"15_CR24","unstructured":"Zhu, J.J., Ungar, L.H.: String edit analysis for merging databases. In: KDD 2000 workshop on text mining, held at the 6th ACM SIGKDD conference, Boston (August 2000)"}],"container-title":["Lecture Notes in Computer Science","Intelligent Data Engineering and Automated Learning - IDEAL 2005"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11508069_15.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,10]],"date-time":"2021-11-10T13:04:21Z","timestamp":1636549461000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11508069_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2005]]},"ISBN":["9783540269724","9783540316930"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/11508069_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2005]]}}}