{"id":"https://openalex.org/W2026147624","doi":"https://doi.org/10.14778/1920841.1920897","title":"Record linkage with uniqueness constraints and erroneous values","display_name":"Record linkage with uniqueness constraints and erroneous values","publication_year":2010,"publication_date":"2010-09-01","ids":{"openalex":"https://openalex.org/W2026147624","doi":"https://doi.org/10.14778/1920841.1920897","mag":"2026147624"},"language":"en","primary_location":{"id":"doi:10.14778/1920841.1920897","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1920841.1920897","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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":"Proceedings of the VLDB Endowment","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/A5055813479","display_name":"Songtao Guo","orcid":"https://orcid.org/0000-0001-6741-4871"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Songtao Guo","raw_affiliation_strings":["AT&T Interactive Research","AT&T Interactive Research#TAB#"],"affiliations":[{"raw_affiliation_string":"AT&T Interactive Research","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"AT&T Interactive Research#TAB#","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001402526","display_name":"Xin Luna Dong","orcid":"https://orcid.org/0009-0000-8667-322X"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Luna Dong","raw_affiliation_strings":["AT&T Labs-Research"],"affiliations":[{"raw_affiliation_string":"AT&T Labs-Research","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088315797","display_name":"Divesh Srivastava","orcid":"https://orcid.org/0000-0002-7609-9217"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Divesh Srivastava","raw_affiliation_strings":["AT&T Labs-Research"],"affiliations":[{"raw_affiliation_string":"AT&T Labs-Research","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109828975","display_name":"R\u00e9mi Zajac","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Remi Zajac","raw_affiliation_strings":["AT&T Interactive Research","AT&T Interactive Research#TAB#"],"affiliations":[{"raw_affiliation_string":"AT&T Interactive Research","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"AT&T Interactive Research#TAB#","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5055813479"],"corresponding_institution_ids":["https://openalex.org/I1283103587"],"apc_list":null,"apc_paid":null,"fwci":6.0785,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.96010786,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"3","issue":"1-2","first_page":"417","last_page":"428"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9864000082015991,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9643999934196472,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/uniqueness","display_name":"Uniqueness","score":0.7888888120651245},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6584764719009399},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.5487178564071655},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5383878946304321},{"id":"https://openalex.org/keywords/record-linkage","display_name":"Record linkage","score":0.5166283249855042},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4593626856803894},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32107383012771606},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19198471307754517},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17894062399864197}],"concepts":[{"id":"https://openalex.org/C2777021972","wikidata":"https://www.wikidata.org/wiki/Q22976830","display_name":"Uniqueness","level":2,"score":0.7888888120651245},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6584764719009399},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.5487178564071655},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5383878946304321},{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.5166283249855042},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4593626856803894},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32107383012771606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19198471307754517},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17894062399864197},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/1920841.1920897","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1920841.1920897","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"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":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W118161007","https://openalex.org/W1535035109","https://openalex.org/W1550159952","https://openalex.org/W1646278814","https://openalex.org/W1964786778","https://openalex.org/W1979746590","https://openalex.org/W1987971958","https://openalex.org/W2007682403","https://openalex.org/W2008896880","https://openalex.org/W2029064186","https://openalex.org/W2046020929","https://openalex.org/W2051224630","https://openalex.org/W2059009730","https://openalex.org/W2059299892","https://openalex.org/W2069484355","https://openalex.org/W2073545563","https://openalex.org/W2096100960","https://openalex.org/W2108991785","https://openalex.org/W2110411158","https://openalex.org/W2123509976","https://openalex.org/W2133676910","https://openalex.org/W2146057107","https://openalex.org/W2148019918","https://openalex.org/W2162449239","https://openalex.org/W2164456230","https://openalex.org/W2167333415","https://openalex.org/W2222512263","https://openalex.org/W2561675875","https://openalex.org/W2914959486","https://openalex.org/W4238831993","https://openalex.org/W4285719527","https://openalex.org/W6641608569","https://openalex.org/W6645186733","https://openalex.org/W6678414873"],"related_works":["https://openalex.org/W571281153","https://openalex.org/W2949403936","https://openalex.org/W3023806604","https://openalex.org/W2952139525","https://openalex.org/W4301247218","https://openalex.org/W2129818458","https://openalex.org/W4243074410","https://openalex.org/W4289551052","https://openalex.org/W4390756076","https://openalex.org/W2340777379"],"abstract_inverted_index":{"Many":[0],"data-management":[1],"applications":[2],"require":[3],"integrating":[4],"data":[5],"from":[6,121,224,231],"a":[7,56,65,161,180,200,244],"variety":[8],"of":[9,171,192,202,227,247,257],"sources,":[10],"where":[11],"different":[12,22],"sources":[13,122,197],"may":[14,26,123,131,153],"refer":[15,46,93],"to":[16,38,47,92,94,134,164,175,240,243],"the":[17,42,48,69,95,102,128,135,177,196,205,228,232,248],"same":[18,49,96,206],"real-world":[19,59,97],"entity":[20,60],"in":[21,34,188,204],"ways":[23],"and":[24,40,78,99,105,138,186,195,213,216,221,255],"some":[25,53],"even":[27],"provide":[28],"erroneous":[29,119],"data.":[30],"An":[31],"important":[32,155],"task":[33],"this":[35,83,166],"process":[36],"is":[37,174],"recognize":[39],"merge":[41],"various":[43],"references":[44],"that":[45,89,198],"entity.":[50],"In":[51,234],"practice,":[52],"attributes":[54],"satisfy":[55],"uniqueness":[57,136,141,249],"constraint---each":[58],"(or":[61],"most":[62],"entities)":[63],"has":[64],"unique":[66],"value":[67,230],"for":[68,115,150],"attribute":[70,193],"(":[71],"e.g.":[72],",":[73],"business":[74],"contact":[75],"phone,":[76],"address,":[77],"email).":[79],"Traditional":[80],"techniques":[81],"tackle":[82],"case":[84],"by":[85],"first":[86],"linking":[87],"records":[88,104,152],"are":[90],"likely":[91],"entity,":[98],"then":[100],"fusing":[101],"linked":[103,151],"resolving":[106,148],"conflicts":[107,149],"if":[108],"any.":[109],"Such":[110],"methods":[111],"can":[112,142,217],"fall":[113],"short":[114],"three":[116],"reasons:":[117],"first,":[118],"values":[120,194,203,220],"prevent":[124],"correct":[125,144,229],"linking;":[126],"second,":[127],"real":[129],"world":[130],"contain":[132],"exceptions":[133],"constraints":[137],"always":[139],"enforcing":[140],"miss":[143],"values;":[145],"third,":[146],"locally":[147],"overlook":[154],"global":[156,211],"evidence.":[157],"This":[158],"paper":[159],"proposes":[160],"novel":[162],"technique":[163],"solve":[165],"problem.":[167],"The":[168],"key":[169],"component":[170],"our":[172,238,258],"solution":[173],"reduce":[176],"problem":[178,185],"into":[179],"k":[181],"-partite":[182],"graph":[183],"clustering":[184,189],"consider":[187],"both":[190],"similarity":[191],"associate":[199],"pair":[201],"record.":[207],"Thus,":[208],"we":[209,236],"perform":[210],"linkage":[212],"fusion":[214],"simultaneously,":[215],"identify":[218],"incorrect":[219],"differentiate":[222],"them":[223],"alternative":[225],"representations":[226],"beginning.":[233],"addition,":[235],"extend":[237],"algorithm":[239],"be":[241],"tolerant":[242],"few":[245],"violations":[246],"constraints.":[250],"Experimental":[251],"results":[252],"show":[253],"accuracy":[254],"scalability":[256],"technique.":[259]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":2}],"updated_date":"2026-03-31T07:56:22.981413","created_date":"2025-10-10T00:00:00"}