{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T04:15:19Z","timestamp":1742962519474,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319467580"},{"type":"electronic","value":"9783319467597"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"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":[[2016]]},"DOI":"10.1007\/978-3-319-46759-7_14","type":"book-chapter","created":{"date-parts":[[2016,9,25]],"date-time":"2016-09-25T23:38:43Z","timestamp":1474846723000},"page":"181-195","source":"Crossref","is-referenced-by-count":8,"title":["An Experimental Survey of MapReduce-Based Similarity Joins"],"prefix":"10.1007","author":[{"given":"Yasin N.","family":"Silva","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jason","family":"Reed","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyle","family":"Brown","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adelbert","family":"Wadsworth","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuitian","family":"Rong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,9,27]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Silva, Y.N., Aref, W.G., Ali, M.: The similarity join database operator. In: ICDE (2010)","DOI":"10.1109\/ICDE.2010.5447873"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Silva, Y.N., Pearson, S.: Exploiting database similarity joins for metric spaces. In: VLDB (2012)","DOI":"10.1145\/2213836.2213935"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Silva, Y.N., Aly, A.M., Aref, W.G., Larson, P.-A.: SimDB: a similarity-aware database system. In: SIGMOD (2010)","DOI":"10.1145\/1807167.1807330"},{"issue":"3","key":"14_CR4","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1007\/s00778-012-0296-4","volume":"22","author":"YN Silva","year":"2013","unstructured":"Silva, Y.N., Aref, W.G., Larson, P.-A., Pearson, S., Ali, M.: Similarity queries: their conceptual evaluation, transformations, and processing. VLDB J. 22(3), 395\u2013420 (2013)","journal-title":"VLDB J."},{"key":"14_CR5","unstructured":"Silva, Y.N., Aref, W.G.: Similarity-aware query processing and optimization. In: VLDB Ph.D. Workshop, France (2009)"},{"issue":"2","key":"14_CR6","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1145\/2350036.2350045","volume":"41","author":"PA Bernstein","year":"2012","unstructured":"Bernstein, P.A., Jensen, C.S., Tan, K.-L.: A call for surveys. SIGMOD Rec. 41(2), 47 (2012)","journal-title":". SIGMOD Rec."},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Chaiken, R., Jenkins, B., Larson, P.-A., Ramsey, B., Shakib, D., Weaver, S., Zhou, J.: Scope: easy and efficient parallel processing of massive data sets. In: VLDB (2008)","DOI":"10.14778\/1454159.1454166"},{"issue":"2","key":"14_CR8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1365815.1365816","volume":"26","author":"F Chang","year":"2008","unstructured":"Chang, F., Dean, J., Ghemawat, S., Hsieh, W.C., Wallach, D.A., Burrows, M., Chandra, T., Fikes, A., Gruber, R.E.: Bigtable: a distributed storage system for structured data. ACM Trans. Comput. Syst. 26(2), 1\u201326 (2008)","journal-title":"ACM Trans. Comput. Syst."},{"key":"14_CR9","unstructured":"Dean, J., Ghemawat, S.: MapReduce: simplified data processing on large clusters. In: OSDI (2004)"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Ghemawat, S., Gobioff, H., Leung, S.-T.: The Google file system. In: SOSP (2003)","DOI":"10.1145\/945445.945450"},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"Isard, M., Budiu, M., Yu, Y., Birrell, A., Fetterly, D.: Dryad: distributed data-parallel programs from sequential building blocks. In: EuroSys (2007)","DOI":"10.1145\/1272996.1273005"},{"key":"14_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1007\/978-3-540-45227-0_48","volume-title":"Database and Expert Systems Applications","author":"V Dohnal","year":"2003","unstructured":"Dohnal, V., Gennaro, C., Zezula, P.: Similarity join in metric spaces using eD-index. In: Ma\u0159\u00edk, V., \u0160t\u011bp\u00e1nkov\u00e1, O., Retschitzegger, W. (eds.) DEXA 2003. LNCS, vol. 2736, pp. 484\u2013493. Springer, Heidelberg (2003). doi: 10.1007\/978-3-540-45227-0_48"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"B\u00f6hm, C., Braunm\u00fcller, B., Krebs, F., Kriegel, H.-P.: Epsilon grid order: an algorithm for the similarity join on massive high-dimensional data. In: SIGMOD (2001)","DOI":"10.1145\/375663.375714"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Dittrich, J.-P., Seeger, B.: GESS: a scalable similarity join algorithm for mining large data sets in high dimensional spaces. In: SIGKDD (2001)","DOI":"10.1145\/502512.502524"},{"key":"14_CR15","doi-asserted-by":"crossref","first-page":"7:1","DOI":"10.1145\/1366102.1366104","volume":"33","author":"EH Jacox","year":"2008","unstructured":"Jacox, E.H., Samet, H.: Metric space similarity joins. ACM Trans. Database Syst. 33, 7:1\u20137:38 (2008)","journal-title":"ACM Trans. Database Syst."},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Chaudhuri, S., Ganti, V., Kaushik, R.: A primitive operator for similarity joins in data cleaning. In: ICDE (2006)","DOI":"10.1109\/ICDE.2006.9"},{"issue":"2","key":"14_CR17","first-page":"60","volume":"29","author":"S Chaudhuri","year":"2006","unstructured":"Chaudhuri, S., Ganti, V., Kaushik, R.: Data debugger: an operator-centric approach for data quality solutions. IEEE Data Eng. Bull. 29(2), 60\u201366 (2006)","journal-title":"IEEE Data Eng. Bull."},{"key":"14_CR18","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)"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Vernica, R., Carey, M.J., Li, C.: Efficient parallel set-similarity joins using MapReduce. In: SIGMOD 2010 (2010)","DOI":"10.1145\/1807167.1807222"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Silva, Y.N., Reed, J.M., Tsosie, L.M.: MapReduce-based similarity join for metric spaces. In: VLDB\/Cloud-I (2012)","DOI":"10.1145\/2347673.2347676"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Silva, Y.N., Reed, J.M.: Exploiting MapReduce-based similarity joins. In: SIGMOD (2012)","DOI":"10.1145\/2213836.2213935"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Afrati, F.N., Sarma, A.D., Menestrina, D., Parameswaran, A., Ullman, J.D.: Fuzzy joins using MapReduce. In: ICDE (2012)","DOI":"10.1109\/ICDE.2012.66"},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Okcan, A., Riedewald, M.: Processing theta-joins using MapReduce. In: SIGMOD (2011)","DOI":"10.1145\/1989323.1989423"},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"Metwally, A., Faloutsos, C.: V-SMART-join: a scalable MapReduce framework for all-pair similarity joins of multisets and vectors. In: VLDB (2012)","DOI":"10.14778\/2212351.2212353"},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Xiao, C., Wang, W., Lin, X., Yu, J.X.: Efficient similarity joins for near duplicate detection. In: WWW (2008)","DOI":"10.1145\/1367497.1367516"},{"key":"14_CR26","unstructured":"Apache Hadoop. http:\/\/hadoop.apache.org\/"},{"key":"14_CR27","unstructured":"SimCloud Project: MapReduce-based similarity join survey. http:\/\/www.public.asu.edu\/~ynsilva\/SimCloud\/SJSurvey"},{"key":"14_CR28","unstructured":"Harvard Library: Harvard bibliographic dataset. http:\/\/library.harvard.edu\/open-metadata"}],"container-title":["Lecture Notes in Computer Science","Similarity Search and Applications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-46759-7_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,13]],"date-time":"2019-09-13T20:28:17Z","timestamp":1568406497000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-46759-7_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319467580","9783319467597"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-46759-7_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]}}}