{"id":"https://openalex.org/W2114764731","doi":"https://doi.org/10.14778/2021017.2021020","title":"Entity matching","display_name":"Entity matching","publication_year":2011,"publication_date":"2011-07-01","ids":{"openalex":"https://openalex.org/W2114764731","doi":"https://doi.org/10.14778/2021017.2021020","mag":"2114764731"},"language":"en","primary_location":{"id":"doi:10.14778/2021017.2021020","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2021017.2021020","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/A5101850961","display_name":"Jiannan Wang","orcid":"https://orcid.org/0009-0002-8978-312X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiannan Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451576","display_name":"Guoliang Li","orcid":"https://orcid.org/0000-0002-1398-0621"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoliang Li","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"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, China"],"affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100951661","display_name":"Jianhua Feng","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Feng","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101850961"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":6.5555,"has_fulltext":false,"cited_by_count":123,"citation_normalized_percentile":{"value":0.96737789,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"4","issue":"10","first_page":"622","last_page":"633"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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":1.0,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9781000018119812,"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"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9775999784469604,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.7420635223388672},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7217022180557251},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7100296020507812},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6125643253326416},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5494850277900696},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4104040861129761},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34106171131134033},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19998016953468323},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.05587714910507202}],"concepts":[{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.7420635223388672},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7217022180557251},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7100296020507812},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6125643253326416},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5494850277900696},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4104040861129761},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34106171131134033},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19998016953468323},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.05587714910507202},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/2021017.2021020","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2021017.2021020","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":[{"display_name":"Industry, innovation and infrastructure","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1485156179","https://openalex.org/W1646278814","https://openalex.org/W1964786778","https://openalex.org/W1990313671","https://openalex.org/W2007682403","https://openalex.org/W2024770506","https://openalex.org/W2034190452","https://openalex.org/W2036216970","https://openalex.org/W2067566391","https://openalex.org/W2073471108","https://openalex.org/W2096598900","https://openalex.org/W2108991785","https://openalex.org/W2111625757","https://openalex.org/W2121516976","https://openalex.org/W2143124645","https://openalex.org/W2154711808","https://openalex.org/W2154785834","https://openalex.org/W2164456230","https://openalex.org/W2171574281","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W1495042958","https://openalex.org/W2494338568","https://openalex.org/W2122678784","https://openalex.org/W2282510344","https://openalex.org/W139987158","https://openalex.org/W2183994405","https://openalex.org/W1972035260","https://openalex.org/W4234013965","https://openalex.org/W2349023125","https://openalex.org/W4253006236"],"abstract_inverted_index":{"Entity":[0],"matching":[1],"that":[2,113,163],"finds":[3],"records":[4],"referring":[5],"to":[6,27,51,65,76,101,126,139,147],"the":[7,29,149,171],"same":[8],"entity":[9,43],"is":[10,47,55,62,98],"an":[11,111,124],"important":[12],"operation":[13],"in":[14],"data":[15],"cleaning":[16],"and":[17,33,39,89,106,117,121,143,159,169],"integration.":[18],"Existing":[19],"studies":[20],"usually":[21],"use":[22],"a":[23,48,83],"given":[24],"similarity":[25,30,69,87,104,115,129,151],"function":[26],"quantify":[28],"of":[31,86],"records,":[32],"focus":[34],"on":[35,156],"devising":[36],"index":[37],"structures":[38],"algorithms":[40,146],"for":[41,57],"efficient":[42,145],"matching.":[44],"However":[45],"it":[46,61,97],"big":[49],"challenge":[50],"define":[52],"\"how":[53],"similar":[54],"similar\"":[56],"real":[58,158],"applications,":[59],"since":[60],"rather":[63,99],"hard":[64],"automatically":[66],"select":[67],"appropriate":[68,103],"functions.":[70,130,152],"In":[71],"this":[72,78,132],"paper":[73],"we":[74,109,122,134],"attempt":[75],"address":[77],"problem.":[79],"As":[80],"there":[81],"are":[82],"large":[84],"number":[85],"functions,":[88],"even":[90],"worse":[91],"thresholds":[92,118],"may":[93],"have":[94,110,119,123],"infinite":[95],"values,":[96],"expensive":[100],"find":[102,148],"functions":[105,116],"thresholds.":[107],"Fortunately,":[108],"observation":[112],"different":[114],"redundancy,":[120,142],"opportunity":[125],"prune":[127],"inappropriate":[128],"To":[131],"end,":[133],"propose":[135],"effective":[136],"optimization":[137],"techniques":[138],"eliminate":[140],"such":[141],"devise":[144],"best":[150],"The":[153],"experimental":[154],"results":[155],"both":[157],"synthetic":[160],"datasets":[161],"show":[162],"our":[164],"method":[165],"achieves":[166],"high":[167],"accuracy":[168],"outperforms":[170],"baseline":[172],"algorithms.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":9},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}