{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T14:35:03Z","timestamp":1759847703984},"publisher-location":"Berlin, Heidelberg","reference-count":21,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540220640"},{"type":"electronic","value":"9783540247753"}],"license":[{"start":{"date-parts":[[2004,1,1]],"date-time":"2004-01-01T00:00:00Z","timestamp":1072915200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2004]]},"DOI":"10.1007\/978-3-540-24775-3_75","type":"book-chapter","created":{"date-parts":[[2010,9,10]],"date-time":"2010-09-10T19:48:20Z","timestamp":1284148100000},"page":"638-647","source":"Crossref","is-referenced-by-count":52,"title":["Febrl \u2013 A Parallel Open Source Data Linkage System"],"prefix":"10.1007","author":[{"given":"Peter","family":"Christen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tim","family":"Churches","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Markus","family":"Hegland","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"75_CR1","unstructured":"Baxter, R., Christen, P., Churches, T.: A Comparison of Fast Blocking Methods for Record Linkage. In: ACM SIGKDD 2003 Workshop on Data Cleaning, Record Linkage, and Object Consolidation, Washington, DC, August 27, pp. 25\u201327 (2003)"},{"key":"75_CR2","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 the 2003 ACM SIGMOD International Conference on on Management of Data, San Diego, USA, pp. 313\u2013324 (2003)","DOI":"10.1145\/872757.872796"},{"key":"75_CR3","doi-asserted-by":"crossref","unstructured":"Churches, T., Christen, P., Lim, K., Zhu, J.X.: Preparation of name and address data for record linkage using hidden Markov models. BioMed Central Medical Informatics and Decision Making (December 2002), Available online at \n                    \n                      http:\/\/www.biomedcentral.com\/1472-6947\/2\/9\/","DOI":"10.1186\/1472-6947-2-9"},{"key":"75_CR4","doi-asserted-by":"crossref","unstructured":"Cohen, W.: Integration of heterogeneous databases without common domains using queries based on textual similarity. In: Proceedings of SIGMOD, Seattle (1998)","DOI":"10.1145\/276304.276323"},{"key":"75_CR5","unstructured":"Elfeky, M.G., Verykios, V.S., Elmagarmid, A.K.: TAILOR: A Record Linkage Toolbox. In: Proceedings of the ICDE 2002, San Jose, USA (2002)"},{"key":"75_CR6","doi-asserted-by":"crossref","unstructured":"Fellegi, I., Sunter, A.: A theory for record linkage. Journal of the American Statistical Society (1969)","DOI":"10.2307\/2286061"},{"key":"75_CR7","unstructured":"Galhardas, H., Florescu, D., Shasha, D., Simon, E.: An Extensible Framework for Data Cleaning. In: Proceedings of the Inter. Conference on Data Engineering (2000)"},{"key":"75_CR8","doi-asserted-by":"crossref","first-page":"C335","DOI":"10.21914\/anziamj.v44i0.685","volume":"44","author":"M. Hegland","year":"2003","unstructured":"Hegland, M.: Adaptive sparse grids. ANZIAM J.\u00a044, C335\u2013C353 (2003)","journal-title":"ANZIAM J."},{"key":"75_CR9","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 (1995)","DOI":"10.1145\/223784.223807"},{"key":"75_CR10","volume-title":"Data Mining and Knowledge Discovery 2","author":"M.A. Hernandez","year":"1998","unstructured":"Hernandez, M.A., Stolfo, S.J.: Real-world data is dirty: Data cleansing and the merge\/purge problem. In: Data Mining and Knowledge Discovery 2, Kluwer Academic Publishers, Dordrecht (1998)"},{"key":"75_CR11","unstructured":"Maletic, J.I., Marcus, A.: Data Cleansing: Beyond Integrity Analysis. In: Proceedings of the Conference on Information Quality (IQ 2000) (October 2000)"},{"key":"75_CR12","doi-asserted-by":"crossref","unstructured":"McCallum, A., Nigam, K., Ungar, L.H.: Efficient clustering of high-dimensional data sets with application to reference matching. Knowledge Discovery and Data Mining, 169\u2013178 (2000)","DOI":"10.1145\/347090.347123"},{"key":"75_CR13","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/7056.001.0001","volume-title":"Using MPI \u2013 Portable Parallel Programming with the Message Passing Interface","author":"W. Gropp","year":"1999","unstructured":"Gropp, W., Lusk, E., Skjellum, A.: Using MPI \u2013 Portable Parallel Programming with the Message Passing Interface, 2nd edn. MIT Press, Cambridge (1999)","edition":"2"},{"key":"75_CR14","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":"75_CR15","doi-asserted-by":"crossref","unstructured":"Newcombe, H.B., Kennedy, J.M.: Record Linkage: Making Maximum Use of the Discriminating Power of Identifying Information. Communications of the ACM 5(11) (1962)","DOI":"10.1145\/368996.369026"},{"key":"75_CR16","unstructured":"Porter, E., Winkler, W.E.: Approximate String Comparison and its Effect on an Advanced Record Linkage System. RR 1997-02, US Bureau of the Census (1997)"},{"key":"75_CR17","doi-asserted-by":"crossref","unstructured":"Rabiner, L.R.: A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition. Proceedings of the IEEE 77(2) (February 1989)","DOI":"10.1109\/5.18626"},{"key":"75_CR18","unstructured":"Rahm, E., Do, H.H.: Data Cleaning: Problems and Current Approaches. IEEE Data Engineering Bulletin (2000)"},{"key":"75_CR19","unstructured":"Winkler, W.E.: The State of Record Linkage and Current Research Problems. RR 1999-04, US Bureau of the Census (1999)"},{"key":"75_CR20","unstructured":"Winkler, W.E.: Using the EM algorithm for weight computation in the Fellegi- Sunter model of record linkage. RR 2000-05, US Bureau of the Census (2000)"},{"key":"75_CR21","unstructured":"Yancey, W.E.: BigMatch: A Program for Extracting Probable Matches from a Large File for Record Linkage. RR 2002-01, US Bureau of the Census (March 2002)"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-24775-3_75","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,19]],"date-time":"2019-05-19T18:06:17Z","timestamp":1558289177000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-24775-3_75"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2004]]},"ISBN":["9783540220640","9783540247753"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-24775-3_75","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2004]]}}}