{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T21:25:08Z","timestamp":1770153908368,"version":"3.49.0"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2021,3,13]],"date-time":"2021-03-13T00:00:00Z","timestamp":1615593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,3,13]],"date-time":"2021-03-13T00:00:00Z","timestamp":1615593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["The VLDB Journal"],"published-print":{"date-parts":[[2021,7]]},"DOI":"10.1007\/s00778-021-00656-7","type":"journal-article","created":{"date-parts":[[2021,3,13]],"date-time":"2021-03-13T09:05:48Z","timestamp":1615626348000},"page":"537-557","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Efficient and effective ER with progressive blocking"],"prefix":"10.1007","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2529-4036","authenticated-orcid":false,"given":"Sainyam","family":"Galhotra","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Donatella","family":"Firmani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Barna","family":"Saha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Divesh","family":"Srivastava","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,3,13]]},"reference":[{"issue":"11","key":"656_CR1","first-page":"999","volume":"7","author":"Y Altowim","year":"2014","unstructured":"Altowim, Y., Kalashnikov, D.V., Mehrotra, S.: Progressive approach to relational entity resolution. PVLDB 7(11), 999\u20131010 (2014)","journal-title":"PVLDB"},{"key":"656_CR2","doi-asserted-by":"crossref","unstructured":"Bilenko, M., Kamath, B., Mooney, R.J.: Adaptive blocking: learning to scale up record linkage. In: ICDM (2006)","DOI":"10.1109\/ICDM.2006.13"},{"key":"656_CR3","doi-asserted-by":"crossref","unstructured":"Christen, P., Churches, T., Hegland, M.: Febrl-a parallel open source data linkage system. In: Pacific-Asia Conference on Knowledge Discovery and Data Mining. Springer, pp. 638\u2013647 (2004)","DOI":"10.1007\/978-3-540-24775-3_75"},{"key":"656_CR4","unstructured":"Crescenzi, V., Angelis, A. D., Firmani, D., Mazzei, M., Merialdo, P., Piai, F., Srivastava, D.: Alaska: a flexible benchmark for data integration tasks (2021)"},{"key":"656_CR5","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1016\/j.is.2018.02.005","volume":"75","author":"G dal Bianco","year":"2018","unstructured":"dal Bianco, G., Gon\u00e7alves, M.A., Duarte, D.: Bloss: effective meta-blocking with almost no effort. Inf. Syst. 75, 75\u201389 (2018)","journal-title":"Inf. Syst."},{"key":"656_CR6","doi-asserted-by":"crossref","unstructured":"Das, S., Paul Suganthan, G.C., Doan, A., Naughton, J.F., Krishnan, G., Deep, R., Arcaute, E., Raghavendra, V., Park, Y.: Falcon: Scaling up hands-off crowdsourced entity matching to build cloud services. In: SIGMOD (2017)","DOI":"10.1145\/3035918.3035960"},{"issue":"1","key":"656_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TKDE.2007.250581","volume":"19","author":"AK Elmagarmid","year":"2007","unstructured":"Elmagarmid, A.K., Ipeirotis, P.G., Verykios, V.S.: Duplicate record detection: a survey. IEEE Trans. Knowl. Data Eng. 19(1), 1\u201316 (2007)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"5","key":"656_CR8","first-page":"384","volume":"9","author":"D Firmani","year":"2016","unstructured":"Firmani, D., Saha, B., Srivastava, D.: Online entity resolution using an oracle. PVLDB 9(5), 384\u2013395 (2016)","journal-title":"PVLDB"},{"key":"656_CR9","doi-asserted-by":"crossref","unstructured":"Galhotra, S., Firmani, D., Saha, B., Srivastava, D.: Robust entity resolution using random graphs. In: SIGMOD (2018)","DOI":"10.1145\/3183713.3183755"},{"key":"656_CR10","doi-asserted-by":"crossref","unstructured":"Gokhale, C., Das, S., Doan, A., Naughton, J.F., Rampalli, N., Shavlik, J., Zhu, X.: Corleone: hands-off crowdsourcing for entity matching. In: SIGMOD (2014)","DOI":"10.1145\/2588555.2588576"},{"key":"656_CR11","first-page":"491","volume":"1","author":"L Gravano","year":"2001","unstructured":"Gravano, L., Ipeirotis, P.G., Jagadish, H.V., Koudas, N., Muthukrishnan, S., Srivastava, D.: Approximate string joins in a database (almost) for free. VLDB 1, 491\u2013500 (2001)","journal-title":"VLDB"},{"issue":"9","key":"656_CR12","first-page":"697","volume":"7","author":"A Gruenheid","year":"2014","unstructured":"Gruenheid, A., Dong, X.L., Srivastava, D.: Incremental record linkage. PVLDB 7(9), 697\u2013708 (2014)","journal-title":"PVLDB"},{"key":"656_CR13","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1145\/568271.223807","volume":"24","author":"MA Hern\u00e1ndez","year":"1995","unstructured":"Hern\u00e1ndez, M.A., Stolfo, S.J.: The merge\/purge problem for large databases. ACM Sigmod Rec. 24, 127\u2013138 (1995)","journal-title":"ACM Sigmod Rec."},{"key":"656_CR14","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1007\/978-1-4612-0865-5_26","volume-title":"The Collected Works of Wassily Hoeffding","author":"W Hoeffding","year":"1994","unstructured":"Hoeffding, W.: Probability inequalities for sums of bounded random variables. In: Hoeffding, W. (ed.) The Collected Works of Wassily Hoeffding, pp. 409\u2013426. Springer, Berlin (1994)"},{"issue":"12","key":"656_CR15","first-page":"1197","volume":"9","author":"P Konda","year":"2016","unstructured":"Konda, P., Das, S., Paul Suganthan, G.C., Doan, A., Ardalan, A., Ballard, J.R., Li, H., Panahi, F., Zhang, H., Naughton, J., et al.: Magellan: toward building entity matching management systems. PVLDB 9(12), 1197\u20131208 (2016)","journal-title":"PVLDB"},{"key":"656_CR16","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3d object representations for fine-grained categorization. In: 4th International IEEE Workshop on 3D Representation and Recognition (3dRR-13) (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"key":"656_CR17","unstructured":"Manning, C.D., Manning, C.D., Sch\u00fctze, H.: Foundations of statistical natural language processing (1999)"},{"key":"656_CR18","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 ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 169\u2013178 (2000)","DOI":"10.1145\/347090.347123"},{"key":"656_CR19","unstructured":"McNeill, N., Kardes, H., Borthwick, A.: Dynamic record blocking: efficient linking of massive databases in mapreduce. Citeseer (2012)"},{"key":"656_CR20","doi-asserted-by":"crossref","unstructured":"Mudgal, S., Li, H., Rekatsinas, T., Doan, A., Park, Y., Krishnan, G., Deep, R., Arcaute, E., Raghavendra, V.: Deep learning for entity matching: a design space exploration. In: SIGMOD (2018)","DOI":"10.1145\/3183713.3196926"},{"issue":"4","key":"656_CR21","first-page":"312","volume":"9","author":"G Papadakis","year":"2015","unstructured":"Papadakis, G., Alexiou, G., Papastefanatos, G., Koutrika, G.: Schema-agnostic vs schema-based configurations for blocking methods on homogeneous data. PVLDB 9(4), 312\u2013323 (2015)","journal-title":"PVLDB"},{"issue":"12","key":"656_CR22","doi-asserted-by":"publisher","first-page":"2665","DOI":"10.1109\/TKDE.2012.150","volume":"25","author":"G Papadakis","year":"2012","unstructured":"Papadakis, G., Ioannou, E., Palpanas, T., Niederee, C., Nejdl, W.: A blocking framework for entity resolution in highly heterogeneous information spaces. IEEE Trans. Knowl. Data Eng. 25(12), 2665\u20132682 (2012)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"656_CR23","first-page":"1946","volume":"26","author":"G Papadakis","year":"2014","unstructured":"Papadakis, G., Koutrika, G., Palpanas, T., Nejdl, W.: Meta-blocking: taking entity resolutionto the next level. TKDE 26, 1946\u20131960 (2014)","journal-title":"TKDE"},{"key":"656_CR24","doi-asserted-by":"publisher","first-page":"101565","DOI":"10.1016\/j.is.2020.101565","volume":"93","author":"G Papadakis","year":"2020","unstructured":"Papadakis, G., Mandilaras, G., Gagliardelli, L., Simonini, G., Thanos, E., Giannakopoulos, G., Bergamaschi, S., Palpanas, T., Koubarakis, M.: Three-dimensional entity resolution with JedAI. Inf. Sys. 93, 101565 (2020)","journal-title":"Inf. Sys."},{"issue":"14","key":"656_CR25","first-page":"1929","volume":"7","author":"G Papadakis","year":"2014","unstructured":"Papadakis, G., Papastefanatos, G., Koutrika, G.: Supervised meta-blocking. PVLDB 7(14), 1929\u20131940 (2014)","journal-title":"PVLDB"},{"issue":"9","key":"656_CR26","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"},{"issue":"12","key":"656_CR27","first-page":"1950","volume":"11","author":"G Papadakis","year":"2018","unstructured":"Papadakis, G., Tsekouras, L., Thanos, E., Giannakopoulos, G., Palpanas, T., Koubarakis, M.: The return of JedAI: end-to-end entity resolution for structured and semi-structured data. PVLDB 11(12), 1950\u20131953 (2018)","journal-title":"PVLDB"},{"issue":"5","key":"656_CR28","first-page":"1316","volume":"27","author":"T Papenbrock","year":"2015","unstructured":"Papenbrock, T., Heise, A., Naumann, F.: Progressive duplicate detection. TKDE 27(5), 1316\u20131329 (2015)","journal-title":"TKDE"},{"key":"656_CR29","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780198506263.001.0001","volume-title":"Random Geometric Graphs","author":"M Penrose","year":"2003","unstructured":"Penrose, M., et al.: Random Geometric Graphs, vol. 5. Oxford University Press, Oxford (2003)"},{"key":"656_CR30","doi-asserted-by":"crossref","unstructured":"Sch\u00fctze, H., Manning, C.D., Raghavan, P.: Introduction to information retrieval. In: Proceedings of the International Communication of Association for Computing Machinery Conference, pp. 260 (2008)","DOI":"10.1017\/CBO9780511809071"},{"issue":"12","key":"656_CR31","first-page":"1173","volume":"9","author":"G Simonini","year":"2016","unstructured":"Simonini, G., Bergamaschi, S., Jagadish, H.: Blast: a loosely schema-aware meta-blocking approach for entity resolution. PVLDB 9(12), 1173\u20131184 (2016)","journal-title":"PVLDB"},{"issue":"6","key":"656_CR32","doi-asserted-by":"publisher","first-page":"1208","DOI":"10.1109\/TKDE.2018.2852763","volume":"31","author":"G Simonini","year":"2018","unstructured":"Simonini, G., Papadakis, G., Palpanas, T., Bergamaschi, S.: Schema-agnostic progressive entity resolution. IEEE Trans. Knowl. Data Eng. 31(6), 1208\u20131221 (2018)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"656_CR33","doi-asserted-by":"crossref","unstructured":"Verroios, V., Garcia-Molina, H.: Entity resolution with crowd errors. In: ICDE, pp. 219\u2013230 (2015)","DOI":"10.1109\/ICDE.2015.7113286"},{"key":"656_CR34","doi-asserted-by":"crossref","unstructured":"Verroios, V., Garcia-Molina, H., Papakonstantinou, Y.: Waldo: an adaptive human interface for crowd entity resolution. In: SIGMOD (2017)","DOI":"10.1145\/3035918.3035931"},{"issue":"12","key":"656_CR35","first-page":"1071","volume":"7","author":"N Vesdapunt","year":"2014","unstructured":"Vesdapunt, N., Bellare, K., Dalvi, N.: Crowdsourcing algorithms for entity resolution. PVLDB 7(12), 1071\u20131082 (2014)","journal-title":"PVLDB"},{"key":"656_CR36","doi-asserted-by":"crossref","unstructured":"Wang, J., Li, G., Kraska, T., Franklin, M. J., Feng, J.: Leveraging transitive relations for crowdsourced joins. In: SIGMOD (2013)","DOI":"10.1145\/2463676.2465280"},{"issue":"1","key":"656_CR37","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1007\/s00778-013-0315-0","volume":"23","author":"SE Whang","year":"2014","unstructured":"Whang, S.E., Garcia-Molina, H.: Incremental entity resolution on rules and data. VLDB J. 23(1), 77\u2013102 (2014)","journal-title":"VLDB J."},{"issue":"5","key":"656_CR38","first-page":"1111","volume":"25","author":"SE Whang","year":"2013","unstructured":"Whang, S.E., Marmaros, D., Garcia-Molina, H.: Pay-as-you-go entity resolution. TKDE 25(5), 1111\u20131124 (2013)","journal-title":"TKDE"},{"key":"656_CR39","doi-asserted-by":"crossref","unstructured":"Whang, S.E., Menestrina, D., Koutrika, G., Theobald, M., Garcia-Molina, H.: Entity resolution with iterative blocking. In: SIGMOD (2009)","DOI":"10.1145\/1559845.1559870"},{"key":"656_CR40","unstructured":"www.cs.umass.edu\/mccallum\/data\/cora-refs.tar.gz"}],"container-title":["The VLDB Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-021-00656-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00778-021-00656-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-021-00656-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,6,29]],"date-time":"2021-06-29T08:14:21Z","timestamp":1624954461000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00778-021-00656-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,13]]},"references-count":40,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2021,7]]}},"alternative-id":["656"],"URL":"https:\/\/doi.org\/10.1007\/s00778-021-00656-7","relation":{},"ISSN":["1066-8888","0949-877X"],"issn-type":[{"value":"1066-8888","type":"print"},{"value":"0949-877X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3,13]]},"assertion":[{"value":"26 May 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 November 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 February 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 March 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}