{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T19:06:09Z","timestamp":1725563169340},"publisher-location":"Berlin, Heidelberg","reference-count":23,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642151040"},{"type":"electronic","value":"9783642151057"}],"license":[{"start":{"date-parts":[[2010,1,1]],"date-time":"2010-01-01T00:00:00Z","timestamp":1262304000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-3-642-15105-7_25","type":"book-chapter","created":{"date-parts":[[2010,8,30]],"date-time":"2010-08-30T10:21:03Z","timestamp":1283163663000},"page":"309-323","source":"Crossref","is-referenced-by-count":5,"title":["An Efficient Duplicate Record Detection Using q-Grams Array Inverted Index"],"prefix":"10.1007","author":[{"given":"Alfredo","family":"Ferro","sequence":"first","affiliation":[]},{"given":"Rosalba","family":"Giugno","sequence":"additional","affiliation":[]},{"given":"Piera Laura","family":"Puglisi","sequence":"additional","affiliation":[]},{"given":"Alfredo","family":"Pulvirenti","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"25_CR1","doi-asserted-by":"crossref","unstructured":"Aizawa, A., Oyama, K.: A fast linkage detection scheme for multi-source information integration. In: International Workshop on Challenges in Web Information Retrieval and Integration, pp. 30\u201339 (2005)","DOI":"10.1109\/WIRI.2005.2"},{"key":"25_CR2","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, pp. 25\u201327 (2003)"},{"key":"25_CR3","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1145\/141356.141385","volume":"20","author":"A. Chatterjee","year":"1991","unstructured":"Chatterjee, A., Segev, A.: Data manipulation in heterogeneous databases. ACM SIGMOD Record\u00a020, 64\u201368 (1991)","journal-title":"ACM SIGMOD Record"},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Chaudhuri, S., Ganjam, K., Ganti, V., Motwani, R.: Robust and efficient fuzzy match for online data cleaning. In: SIGMOD 2003, pp. 313\u2013324 (2003)","DOI":"10.1145\/872757.872796"},{"key":"25_CR5","first-page":"30","volume":"87","author":"P. Christen","year":"2008","unstructured":"Christen, P., Gayler, R.: Towards scalable real-time entity resolution using a similarity-aware inverted index approach. Proceedings of AusDM 2008, Glenelg, Adelaide\u00a087, 30\u201339 (2008)","journal-title":"Proceedings of AusDM 2008, Glenelg, Adelaide"},{"key":"25_CR6","unstructured":"Christen, P., Churches, T.: Febrl: Freely extensible biomedical record linkage Manual (2002)"},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Cohen, W., Richman, J.: Learning to match and cluster large high-dimensional data sets for data integration. In: SIGKDD 2002 (2002)","DOI":"10.1145\/775047.775116"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Elmagarmid, A., Ipeirotis, P., Verykios, V.: Duplicate record detection: A survey. TKDE\u00a019 (2007)","DOI":"10.1109\/TKDE.2007.250581"},{"key":"25_CR9","unstructured":"Gravano, L., Ipeirotis, P.G., Jagadish, H.V., Koudas, N., Muthukrishnan, S., Srivastava, D.: Approximate string joins in a database (almost) for free. In: VLDB 2001, pp. 491\u2013500 (2001)"},{"key":"25_CR10","volume-title":"The data warehouse ETL toolkit: Practical techniques for extracting, cleaning, conforming, and delivering data","author":"J. Han","year":"2004","unstructured":"Han, J., Kamber, M.: The data warehouse ETL toolkit: Practical techniques for extracting, cleaning, conforming, and delivering data. John Wiley and Sons, Chichester (2004)"},{"key":"25_CR11","unstructured":"Jaro, M.A.: Unimatch: A record linkage system: User\u2019s manual. Technical report, U.S. Bureau of the Census, Washington, D.C (1976)"},{"key":"25_CR12","doi-asserted-by":"publisher","first-page":"414","DOI":"10.1080\/01621459.1989.10478785","volume":"84","author":"M.A. Jaro","year":"1989","unstructured":"Jaro, M.A.: Advances in record linkage methodology as applied to matching the 1985 census of tampa, florida. Journal of the American Statistical Society\u00a084, 414\u2013420 (1989)","journal-title":"Journal of the American Statistical Society"},{"key":"25_CR13","first-page":"845","volume":"163","author":"V.I. Levenshtein","year":"1965","unstructured":"Levenshtein, V.I.: Binary codes capable of correcting deletions, insertions and reversals. Doklady Akademii Nauk SSSR\u00a0163, 845\u2013848 (1965)","journal-title":"Doklady Akademii Nauk SSSR"},{"key":"25_CR14","doi-asserted-by":"crossref","unstructured":"Hernandez, M., Stolfo, S.: The merge\/purge problem for large databases. In: Proceedings of the ACM SIGMOD International Conference on Management of Data (1995)","DOI":"10.1145\/223784.223807"},{"key":"25_CR15","doi-asserted-by":"publisher","first-page":"935","DOI":"10.1137\/0222058","volume":"22","author":"U. Manber","year":"1993","unstructured":"Manber, U., Myers, G.: Suffix arrays: a new method for on-line string searches. SIAM Journal on Computing\u00a022, 935\u2013948 (1993)","journal-title":"SIAM Journal on Computing"},{"key":"25_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: ACM SIGKDD, pp. 169\u2013178 (2000)","DOI":"10.1145\/347090.347123"},{"key":"25_CR17","unstructured":"Monge, A.E., Elkan, C.P.: An efficient domain-independent algorithm for detecting approximately duplicate database records. In: Proceedings of DMKD 1997, pp. 23\u201329 (1997)"},{"key":"25_CR18","unstructured":"Ramos, J.: Using tf-idf to determine word relevance in document queries. In: Proceedings of the First Instructional Conference on Machine Learning (2003)"},{"key":"25_CR19","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":"25_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1007\/3-540-60313-1_153","volume-title":"Algorithms - ESA \u201995","author":"E. Sutinen","year":"1995","unstructured":"Sutinen, E., Tarhio, J.: On using q-gram locations in approximate string matching. In: Spirakis, P.G. (ed.) ESA 1995. LNCS, vol.\u00a0979, pp. 327\u2013340. Springer, Heidelberg (1995)"},{"key":"25_CR21","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1016\/0304-3975(92)90143-4","volume":"92","author":"E. Ukkonen","year":"1992","unstructured":"Ukkonen, E.: Approximate string matching with q-grams and maximal matches. Theoretical Computer Science\u00a092, 191\u2013211 (1992)","journal-title":"Theoretical Computer Science"},{"key":"25_CR22","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1093\/comjnl\/20.2.141","volume":"20","author":"J. Ullman","year":"1977","unstructured":"Ullman, J.: A binary n-gram technique for automatic correction of substitution, deletion, insertion, and reversal errors in words. The Computer Journal\u00a020, 141\u2013147 (1977)","journal-title":"The Computer Journal"},{"key":"25_CR23","unstructured":"Winkler, W.E.: The state of record linkage and current research problems. In: Statistics of Income Division (1999)"}],"container-title":["Lecture Notes in Computer Science","Data Warehousing and Knowledge Discovery"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-15105-7_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,2]],"date-time":"2019-06-02T16:05:26Z","timestamp":1559491526000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-15105-7_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642151040","9783642151057"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-15105-7_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2010]]}}}