{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T23:38:47Z","timestamp":1791070727189,"version":"4.1.0"},"reference-count":18,"publisher":"Association for Computing Machinery (ACM)","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. VLDB Endow."],"published-print":{"date-parts":[[2011,1]]},"abstract":"<jats:p>\n            There have been several recent advancements in Machine Learning community on the Entity Matching (EM) problem. However, their lack of scalability has prevented them from being applied in practical settings on large real-life datasets. Towards this end, we propose a principled framework to scale any generic EM algorithm. Our technique consists of running multiple instances of the EM algorithm on small\n            <jats:italic>neighborhoods<\/jats:italic>\n            of the data and\n            <jats:italic>passing messages<\/jats:italic>\n            across neighborhoods to construct a global solution. We prove formal properties of our framework and experimentally demonstrate the effectiveness of our approach in scaling EM algorithms.\n          <\/jats:p>","DOI":"10.14778\/1938545.1938546","type":"journal-article","created":{"date-parts":[[2014,6,24]],"date-time":"2014-06-24T12:17:57Z","timestamp":1403612277000},"page":"208-218","source":"Crossref","is-referenced-by-count":58,"title":["Large-scale collective entity matching"],"prefix":"10.14778","volume":"4","author":[{"given":"Vibhor","family":"Rastogi","sequence":"first","affiliation":[{"name":"Yahoo! Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nilesh","family":"Dalvi","sequence":"additional","affiliation":[{"name":"Yahoo! Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minos","family":"Garofalakis","sequence":"additional","affiliation":[{"name":"Technical University of Crete"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2011,1]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/1287369.1287420"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2009.43"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/1066157.1066172"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972764.5"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1217299.1217304"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1066157.1066168"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1559845.1559870"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1969.10501049"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1401890.1401931"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972757.24"},{"key":"e_1_2_1_11_1","doi-asserted-by":"crossref","unstructured":"V. Kolmogorov and R. Zabih. What energy functions can be minimized via graph cuts. ECCV (3) pages 65--81 2002.   V. Kolmogorov and R. Zabih. What energy functions can be minimized via graph cuts. ECCV (3) pages 65--81 2002.","DOI":"10.1007\/3-540-47977-5_5"},{"key":"e_1_2_1_12_1","unstructured":"M. Ley. dblp.xml - a documentation: http:\/\/dblp.uni-trier.de\/xml\/docu\/dblpxml.pdf.  M. Ley. dblp.xml - a documentation: http:\/\/dblp.uni-trier.de\/xml\/docu\/dblpxml.pdf."},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/347090.347123"},{"key":"e_1_2_1_14_1","first-page":"905","volume-title":"NIPS","author":"McCallum A.","year":"2004"},{"key":"e_1_2_1_15_1","first-page":"954","volume":"130","author":"Newcombe H. B.","year":"1959","journal-title":"Automatic Linkage of Vital Records. Science"},{"key":"e_1_2_1_16_1","first-page":"31","volume-title":"KDD Workshop on Multi-Relational Data Mining","author":"Domingos P.","year":"2004"},{"key":"e_1_2_1_17_1","first-page":"1401","volume-title":"NIPS","author":"Pasula H.","year":"2002"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2006.65"}],"container-title":["Proceedings of the VLDB Endowment"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.14778\/1938545.1938546","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,28]],"date-time":"2022-12-28T10:45:47Z","timestamp":1672224347000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.14778\/1938545.1938546"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,1]]},"references-count":18,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2011,1]]}},"alternative-id":["10.14778\/1938545.1938546"],"URL":"https:\/\/doi.org\/10.14778\/1938545.1938546","relation":{},"ISSN":["2150-8097"],"issn-type":[{"value":"2150-8097","type":"print"}],"subject":[],"published":{"date-parts":[[2011,1]]}}}