{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T15:03:32Z","timestamp":1786979012342,"version":"build-2736575974"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319930398","type":"print"},{"value":"9783319930404","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-93040-4_8","type":"book-chapter","created":{"date-parts":[[2018,6,16]],"date-time":"2018-06-16T09:29:41Z","timestamp":1529141381000},"page":"89-101","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Using Metric Space Indexing for Complete and Efficient Record Linkage"],"prefix":"10.1007","author":[{"given":"\u00d6zg\u00fcr","family":"Akg\u00fcn","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alan","family":"Dearle","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Graham","family":"Kirby","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Christen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,6,17]]},"reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Bilenko, M., Kamath, B., Mooney, R.J.: Adaptive blocking: learning to scale up record linkage. In: IEEE ICDM, Hong Kong, pp. 87\u201396 (2006)","DOI":"10.1109\/ICDM.2006.13"},{"key":"8_CR2","doi-asserted-by":"publisher","first-page":"1091","DOI":"10.1109\/TPAMI.2007.1078","volume":"29","author":"L Bo","year":"2007","unstructured":"Bo, L., Yujian, L.: A normalized Levenshtein distance metric. IEEE Trans. Pattern Anal. Mach. Intell. 29, 1091\u20131095 (2007). https:\/\/doi.org\/10.1109\/TPAMI.2007.1078","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"8_CR3","unstructured":"Broder, A.: On the resemblance and containment of documents. In: IEEE Compression and Complexity of Sequences, Salerno, Italy, pp. 21\u201329 (1997)"},{"key":"8_CR4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-31164-2","volume-title":"Data Matching - Concepts and Techniques for Record Linkage, Entity Resolution, and Duplicate Detection","author":"P Christen","year":"2012","unstructured":"Christen, P.: Data Matching - Concepts and Techniques for Record Linkage, Entity Resolution, and Duplicate Detection. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-31164-2"},{"issue":"9","key":"8_CR5","first-page":"1537","volume":"24","author":"P Christen","year":"2012","unstructured":"Christen, P.: A survey of indexing techniques for scalable record linkage and deduplication. IEEE TKDE 24(9), 1537\u20131555 (2012)","journal-title":"IEEE TKDE"},{"key":"8_CR6","unstructured":"Ciaccia, P., Patella, M., Rabitti, F., Zezula, P.: Indexing metric spaces with M-tree. In: Italian Symposium on Advanced Database Systems 1997, pp. 67\u201386 (1997)"},{"key":"8_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1007\/978-3-319-46759-7_16","volume-title":"Similarity Search and Applications","author":"R Connor","year":"2016","unstructured":"Connor, R.: A tale of four metrics. In: Amsaleg, L., Houle, M.E., Schubert, E. (eds.) SISAP 2016. LNCS, vol. 9939, pp. 210\u2013217. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46759-7_16"},{"key":"8_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1007\/978-3-319-68474-1_7","volume-title":"Similarity Search and Applications","author":"R Connor","year":"2017","unstructured":"Connor, R., Vadicamo, L., Rabitti, F.: High-dimensional simplexes for supermetric search. In: Beecks, C., Borutta, F., Kr\u00f6ger, P., Seidl, T. (eds.) SISAP 2017. LNCS, pp. 96\u2013109. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-68474-1_7"},{"key":"8_CR9","unstructured":"Dibben, C., Williamson, L., Huang, Z.: Digitising Scotland (2012). http:\/\/gtr.rcuk.ac.uk\/projects?ref=ES\/K00574X\/2"},{"issue":"1","key":"8_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.2200\/S00578ED1V01Y201404DTM040","volume":"7","author":"XL Dong","year":"2015","unstructured":"Dong, X.L., Srivastava, D.: Big data integration. Synth. Lect. Data Manag. 7(1), 1\u2013198 (2015)","journal-title":"Synth. Lect. Data Manag."},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Draisbach, U., Naumann, F., Szott, S., Wonneberg, O.: Adaptive windows for duplicate detection. In: IEEE ICDE, Washington, DC, pp. 1073\u20131083 (2012)","DOI":"10.1109\/ICDE.2012.20"},{"issue":"328","key":"8_CR12","doi-asserted-by":"publisher","first-page":"1183","DOI":"10.1080\/01621459.1969.10501049","volume":"64","author":"IP Fellegi","year":"1969","unstructured":"Fellegi, I.P., Sunter, A.B.: A theory for record linkage. J. Am. Stat. Assoc. 64(328), 1183\u20131210 (1969)","journal-title":"J. Am. Stat. Assoc."},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Fisher, J., Wang, Q.: Unsupervised measuring of entity resolution consistency. In: IEEE ICDM DINA Workshop, pp. 218\u2013221 (2015)","DOI":"10.1109\/ICDMW.2015.162"},{"issue":"3","key":"8_CR14","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1007\/s11222-017-9746-6","volume":"28","author":"D Hand","year":"2018","unstructured":"Hand, D., Christen, P.: A note on using the F-measure for evaluating record linkage algorithms. Stat. Comput. 28(3), 539\u2013547 (2018)","journal-title":"Stat. Comput."},{"issue":"2","key":"8_CR15","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1145\/276305.276326","volume":"27","author":"GR Hjaltason","year":"1998","unstructured":"Hjaltason, G.R., Samet, H.: Incremental distance join algorithms for spatial databases. SIGMOD Rec. 27(2), 237\u2013248 (1998)","journal-title":"SIGMOD Rec."},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Indyk, P., Motwani, R.: Approximate nearest neighbors: towards removing the curse of dimensionality. In: ACM TOC, Dallas, pp. 604\u2013613 (1998)","DOI":"10.1145\/276698.276876"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Kejriwal, M., Miranker, D.P.: An unsupervised algorithm for learning blocking schemes. In: IEEE ICDM, Dallas, pp. 340\u2013349 (2013)","DOI":"10.1109\/ICDM.2013.60"},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"Kim, H., Lee, D.: HARRA: fast iterative hashed record linkage for large-scale data collections. In: EDBT, Lausanne, pp. 525\u2013536 (2010)","DOI":"10.1145\/1739041.1739104"},{"key":"8_CR19","first-page":"707","volume":"10","author":"V Levenshtein","year":"1966","unstructured":"Levenshtein, V.: Binary codes capable of correcting deletions, insertions and reversals. Cybern. Control Theory 10, 707\u2013710 (1966)","journal-title":"Cybern. Control Theory"},{"issue":"4","key":"8_CR20","doi-asserted-by":"publisher","first-page":"557","DOI":"10.1007\/s11280-006-0226-8","volume":"9","author":"C Li","year":"2006","unstructured":"Li, C., Jin, L., Mehrotra, S.: Supporting efficient record linkage for large data sets using mapping techniques. World Wide Web 9(4), 557\u2013584 (2006)","journal-title":"World Wide Web"},{"key":"8_CR21","doi-asserted-by":"publisher","unstructured":"McCallum, A.: Cora dataset: cora.csv (2017). https:\/\/doi.org\/10.3886\/E4728V1","DOI":"10.3886\/E4728V1"},{"key":"8_CR22","unstructured":"Michelson, M., Knoblock, C.A.: Learning blocking schemes for record linkage. In: AAAI, Boston (2006)"},{"key":"8_CR23","unstructured":"Monge, A.E., Elkan, C.P.: The field-matching problem: algorithm and applications. In: ACM SIGKDD, Portland, pp. 267\u2013270 (1996)"},{"issue":"3381","key":"8_CR24","doi-asserted-by":"publisher","first-page":"954","DOI":"10.1126\/science.130.3381.954","volume":"130","author":"H Newcombe","year":"1959","unstructured":"Newcombe, H., Kennedy, J., Axford, S., James, A.: Automatic linkage of vital records. Science 130(3381), 954\u2013959 (1959)","journal-title":"Science"},{"issue":"9","key":"8_CR25","first-page":"684","volume":"9","author":"G Papadakis","year":"2016","unstructured":"Papadakis, G., Svirsky, J., Gal, A., Palpanas, T.: Comparative analysis of approximate blocking techniques for entity resolution. PVLDB 9(9), 684\u2013695 (2016)","journal-title":"PVLDB"},{"key":"8_CR26","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"574","DOI":"10.1007\/978-3-319-18032-8_45","volume-title":"Advances in Knowledge Discovery and Data Mining","author":"B Ramadan","year":"2015","unstructured":"Ramadan, B., Christen, P.: Unsupervised blocking key selection for real-time entity resolution. In: Cao, T., Lim, E.-P., Zhou, Z.-H., Ho, T.-B., Cheung, D., Motoda, H. (eds.) PAKDD 2015. LNCS (LNAI), vol. 9078, pp. 574\u2013585. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-18032-8_45"},{"key":"8_CR27","unstructured":"Reid, A., Garrett, E., Davies, R., Blaikie, A.: Scottish census enumerators\u2019 books: Skye, Kilmarnock, Rothiemay and Torthorwald, 1861\u20131901. Economic and Social Data Service (2006)"},{"issue":"1\u20132","key":"8_CR28","doi-asserted-by":"publisher","first-page":"61","DOI":"10.3366\/hac.2002.14.1-2.61","volume":"14","author":"A Reid","year":"2002","unstructured":"Reid, A., Davies, R., Garrett, E.: Nineteenth-century Scottish demography from linked censuses and civil registers: a \u2018sets of related individuals\u2019 approach. History Comput. 14(1\u20132), 61\u201386 (2002)","journal-title":"History Comput."},{"key":"8_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1007\/978-3-319-11257-2_20","volume-title":"Privacy in Statistical Databases","author":"RC Steorts","year":"2014","unstructured":"Steorts, R.C., Ventura, S.L., Sadinle, M., Fienberg, S.E.: A comparison of blocking methods for record linkage. In: Domingo-Ferrer, J. (ed.) PSD 2014. LNCS, vol. 8744, pp. 253\u2013268. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-11257-2_20"},{"key":"8_CR30","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"562","DOI":"10.1007\/978-3-319-18032-8_44","volume-title":"Advances in Knowledge Discovery and Data Mining","author":"Q Wang","year":"2015","unstructured":"Wang, Q., Vatsalan, D., Christen, P.: Efficient interactive training selection for large-scale entity resolution. In: Cao, T., Lim, E.-P., Zhou, Z.-H., Ho, T.-B., Cheung, D., Motoda, H. (eds.) PAKDD 2015. LNCS (LNAI), vol. 9078, pp. 562\u2013573. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-18032-8_44"},{"key":"8_CR31","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-29151-2","volume-title":"Similarity Search: The Metric Space Approach","author":"P Zezula","year":"2010","unstructured":"Zezula, P., Amato, G., Dohnal, V., Batko, M.: Similarity Search: The Metric Space Approach. Springer, Boston (2010). https:\/\/doi.org\/10.1007\/0-387-29151-2"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-93040-4_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T06:53:28Z","timestamp":1710312808000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-93040-4_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319930398","9783319930404"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-93040-4_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"17 June 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Melbourne, VIC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 June 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 June 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/prada-research.net\/pakdd18\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}