{"id":"https://openalex.org/W2065259291","doi":"https://doi.org/10.1145/2000824.2000825","title":"Efficient similarity joins for near-duplicate detection","display_name":"Efficient similarity joins for near-duplicate detection","publication_year":2011,"publication_date":"2011-08-01","ids":{"openalex":"https://openalex.org/W2065259291","doi":"https://doi.org/10.1145/2000824.2000825","mag":"2065259291"},"language":"en","primary_location":{"id":"doi:10.1145/2000824.2000825","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2000824.2000825","pdf_url":null,"source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Database Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036148682","display_name":"Chuan Xiao","orcid":"https://orcid.org/0000-0001-7239-5134"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Chuan Xiao","raw_affiliation_strings":["The University of New South Wales, Australia","the University of New South Wales, Australia#TAB#"],"affiliations":[{"raw_affiliation_string":"The University of New South Wales, Australia","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"the University of New South Wales, Australia#TAB#","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100392089","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0002-8180-2886"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["The University of New South Wales, Australia","the University of New South Wales, Australia#TAB#"],"affiliations":[{"raw_affiliation_string":"The University of New South Wales, Australia","institution_ids":["https://openalex.org/I31746571"]},{"raw_affiliation_string":"the University of New South Wales, Australia#TAB#","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079659938","display_name":"Xuemin Lin","orcid":"https://orcid.org/0000-0003-2396-7225"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]},{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["AU","CN"],"is_corresponding":false,"raw_author_name":"Xuemin Lin","raw_affiliation_strings":["The University of New South Wales, Australia and East China Normal University","The University of New South Wales, Australia and East China Normal University#TAB#"],"affiliations":[{"raw_affiliation_string":"The University of New South Wales, Australia and East China Normal University","institution_ids":["https://openalex.org/I66867065","https://openalex.org/I31746571"]},{"raw_affiliation_string":"The University of New South Wales, Australia and East China Normal University#TAB#","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075642293","display_name":"Jeffrey Xu Yu","orcid":"https://orcid.org/0000-0002-9738-827X"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jeffrey Xu Yu","raw_affiliation_strings":["Chinese University of Hong Kong, Hong Kong","Chinese University of Hong Kong, Hong Kong.#TAB#"],"affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong.#TAB#","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054991337","display_name":"Guoren Wang","orcid":"https://orcid.org/0000-0002-0181-8379"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoren Wang","raw_affiliation_strings":["Northeastern University, China"],"affiliations":[{"raw_affiliation_string":"Northeastern University, China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5036148682"],"corresponding_institution_ids":["https://openalex.org/I31746571"],"apc_list":null,"apc_paid":null,"fwci":27.9323,"has_fulltext":false,"cited_by_count":320,"citation_normalized_percentile":{"value":0.99804727,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"36","issue":"3","first_page":"1","last_page":"41"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9911999702453613,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9098412990570068},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.6812765598297119},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6643221378326416},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6602767705917358},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6057873964309692},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4879893660545349},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4009559750556946},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36000990867614746},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17827391624450684}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9098412990570068},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.6812765598297119},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6643221378326416},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6602767705917358},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6057873964309692},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4879893660545349},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4009559750556946},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36000990867614746},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17827391624450684},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2000824.2000825","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2000824.2000825","pdf_url":null,"source":{"id":"https://openalex.org/S90119964","display_name":"ACM Transactions on Database Systems","issn_l":"0362-5915","issn":["0362-5915","1557-4644"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Database Systems","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.224.6023","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.224.6023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cse.unsw.edu.au/%7Eweiw/files/TODS-PPJoin-Final.pdf","raw_type":"text"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-159460","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-159460","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G602722286","display_name":null,"funder_award_id":"DP0987273DP0881779DP110102937DP0987557DP0881035NSFC61021004","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W46452414","https://openalex.org/W1502916507","https://openalex.org/W1604983895","https://openalex.org/W1609518033","https://openalex.org/W1612155886","https://openalex.org/W1660390307","https://openalex.org/W1860104593","https://openalex.org/W1974995373","https://openalex.org/W1990061958","https://openalex.org/W2001496424","https://openalex.org/W2007842132","https://openalex.org/W2009036829","https://openalex.org/W2012833704","https://openalex.org/W2020919487","https://openalex.org/W2067432306","https://openalex.org/W2067566391","https://openalex.org/W2072173758","https://openalex.org/W2083039049","https://openalex.org/W2085922539","https://openalex.org/W2096598900","https://openalex.org/W2097184821","https://openalex.org/W2097776316","https://openalex.org/W2105423800","https://openalex.org/W2105436061","https://openalex.org/W2107293766","https://openalex.org/W2108991785","https://openalex.org/W2109803107","https://openalex.org/W2111295912","https://openalex.org/W2111549955","https://openalex.org/W2114353347","https://openalex.org/W2117461391","https://openalex.org/W2119057313","https://openalex.org/W2119455368","https://openalex.org/W2121516976","https://openalex.org/W2123020735","https://openalex.org/W2127675794","https://openalex.org/W2132069633","https://openalex.org/W2135223301","https://openalex.org/W2139532006","https://openalex.org/W2142385580","https://openalex.org/W2145349611","https://openalex.org/W2147717514","https://openalex.org/W2148578434","https://openalex.org/W2150916025","https://openalex.org/W2151406030","https://openalex.org/W2152565070","https://openalex.org/W2161936973","https://openalex.org/W2164634022","https://openalex.org/W2167847032","https://openalex.org/W2169189540","https://openalex.org/W2320748401","https://openalex.org/W2666600683","https://openalex.org/W2740009257","https://openalex.org/W4238945254","https://openalex.org/W4250366158","https://openalex.org/W6624626827","https://openalex.org/W6636190696","https://openalex.org/W6679663036"],"related_works":["https://openalex.org/W2088925915","https://openalex.org/W2382891957","https://openalex.org/W2393491644","https://openalex.org/W2067184662","https://openalex.org/W3047837489","https://openalex.org/W2622139626","https://openalex.org/W2133660117","https://openalex.org/W2104496206","https://openalex.org/W3013303285","https://openalex.org/W2385836742"],"abstract_inverted_index":{"With":[0],"the":[1,7,18,57,79,87,93,99,105],"increasing":[2],"amount":[3],"of":[4,17,39,70,107],"data":[5,11,14],"and":[6,90,96,113],"need":[8],"to":[9,22,35,61],"integrate":[10],"from":[12],"multiple":[13],"sources,":[15],"one":[16],"challenging":[19],"issues":[20],"is":[21],"identify":[23],"near-duplicate":[24],"records":[25,40],"efficiently.":[26],"In":[27],"this":[28],"article,":[29],"we":[30],"focus":[31],"on":[32,56,126],"efficient":[33],"algorithms":[34,54,121,125],"find":[36],"a":[37,49],"pair":[38],"such":[41],"that":[42],"their":[43],"similarities":[44],"are":[45,84],"no":[46],"less":[47],"than":[48],"given":[50],"threshold.":[51],"Several":[52],"existing":[53,88],"rely":[55],"prefix":[58],"filtering":[59,75],"principle":[60],"avoid":[62],"computing":[63],"similarity":[64],"values":[65],"for":[66],"all":[67],"possible":[68],"pairs":[69],"records.":[71],"We":[72,101],"propose":[73],"new":[74],"techniques":[76],"by":[77],"exploiting":[78],"token":[80],"ordering":[81],"information;":[82],"they":[83],"integrated":[85],"into":[86],"methods":[89],"drastically":[91],"reduce":[92],"candidate":[94],"sizes":[95],"hence":[97],"improve":[98],"efficiency.":[100],"have":[102],"also":[103],"studied":[104],"implementation":[106],"our":[108,119],"proposed":[109,120],"algorithm":[110],"in":[111],"stand-alone":[112],"RDBMS-based":[114],"settings.":[115],"Experimental":[116],"results":[117],"show":[118],"can":[122],"outperform":[123],"previous":[124],"several":[127],"real":[128],"datasets.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":21},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":27},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":27},{"year":2018,"cited_by_count":36},{"year":2017,"cited_by_count":24},{"year":2016,"cited_by_count":27},{"year":2015,"cited_by_count":35},{"year":2014,"cited_by_count":24},{"year":2013,"cited_by_count":27},{"year":2012,"cited_by_count":13}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2016-06-24T00:00:00"}
