{"id":"https://openalex.org/W3197468999","doi":"https://doi.org/10.14778/3476249.3476294","title":"Deep learning for blocking in entity matching","display_name":"Deep learning for blocking in entity matching","publication_year":2021,"publication_date":"2021-07-01","ids":{"openalex":"https://openalex.org/W3197468999","doi":"https://doi.org/10.14778/3476249.3476294","mag":"3197468999"},"language":"en","primary_location":{"id":"doi:10.14778/3476249.3476294","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3476249.3476294","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/A5066004392","display_name":"Saravanan Thirumuruganathan","orcid":"https://orcid.org/0000-0002-1517-480X"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Saravanan Thirumuruganathan","raw_affiliation_strings":["HBKU, Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HBKU, Qatar","institution_ids":["https://openalex.org/I4210144839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100452600","display_name":"Han Li","orcid":"https://orcid.org/0000-0002-7380-6174"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Han Li","raw_affiliation_strings":["Amazon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101824160","display_name":"Nan Tang","orcid":"https://orcid.org/0000-0003-2832-0295"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Nan Tang","raw_affiliation_strings":["HBKU, Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HBKU, Qatar","institution_ids":["https://openalex.org/I4210144839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026923999","display_name":"Mourad Ouzzani","orcid":"https://orcid.org/0000-0002-4035-3025"},"institutions":[{"id":"https://openalex.org/I4210144839","display_name":"Hamad bin Khalifa University","ror":"https://ror.org/03eyq4y97","country_code":"QA","type":"education","lineage":["https://openalex.org/I4210144839"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Mourad Ouzzani","raw_affiliation_strings":["HBKU, Qatar"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HBKU, Qatar","institution_ids":["https://openalex.org/I4210144839"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088781274","display_name":"Yash Govind","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134847","display_name":"Centro Tecnol\u00f3gico de Investigaci\u00f3n, Desarrollo e Innovaci\u00f3n en tecnolog\u00edas de la Informaci\u00f3n y las Comunicaciones (TIC)","ror":"https://ror.org/02s69db58","country_code":"ES","type":"nonprofit","lineage":["https://openalex.org/I4210134847"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Yash Govind","raw_affiliation_strings":["Informatica"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Informatica","institution_ids":["https://openalex.org/I4210134847"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004171621","display_name":"Derek J. Paulsen","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Derek Paulsen","raw_affiliation_strings":["UW-Madison"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UW-Madison","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111408590","display_name":"Glenn Fung","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113097","display_name":"Aflac (United States)","ror":"https://ror.org/01d3smq07","country_code":"US","type":"company","lineage":["https://openalex.org/I4210113097"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Glenn Fung","raw_affiliation_strings":["American Family Insurance"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"American Family Insurance","institution_ids":["https://openalex.org/I4210113097"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110256670","display_name":"AnHai Doan","orcid":null},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"AnHai Doan","raw_affiliation_strings":["UW-Madison"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UW-Madison","institution_ids":["https://openalex.org/I135310074"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.7618,"has_fulltext":false,"cited_by_count":83,"citation_normalized_percentile":{"value":0.97857539,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"14","issue":"11","first_page":"2459","last_page":"2472"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9915000200271606,"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/T10028","display_name":"Topic Modeling","score":0.973800003528595,"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/computer-science","display_name":"Computer science","score":0.7725130319595337},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.7639322280883789},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6656871438026428},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6242843270301819},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5331515669822693},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47393423318862915},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4350232779979706},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4170502722263336},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3747404217720032},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.333318829536438},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12764081358909607}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7725130319595337},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.7639322280883789},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6656871438026428},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6242843270301819},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5331515669822693},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47393423318862915},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4350232779979706},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4170502722263336},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3747404217720032},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.333318829536438},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12764081358909607},{"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3476249.3476294","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3476249.3476294","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":[{"id":"https://metadata.un.org/sdg/9","score":0.6100000143051147,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":86,"referenced_works":["https://openalex.org/W343636949","https://openalex.org/W1504263697","https://openalex.org/W1532499126","https://openalex.org/W1540269031","https://openalex.org/W1724849505","https://openalex.org/W1870305865","https://openalex.org/W1992930793","https://openalex.org/W1995099886","https://openalex.org/W2003684739","https://openalex.org/W2031250218","https://openalex.org/W2036216970","https://openalex.org/W2042458413","https://openalex.org/W2064675550","https://openalex.org/W2079649893","https://openalex.org/W2107966677","https://openalex.org/W2108991785","https://openalex.org/W2111116800","https://openalex.org/W2145094598","https://openalex.org/W2162630660","https://openalex.org/W2171574281","https://openalex.org/W2216499221","https://openalex.org/W2250539671","https://openalex.org/W2286724461","https://openalex.org/W2398333000","https://openalex.org/W2493916176","https://openalex.org/W2535168187","https://openalex.org/W2542998387","https://openalex.org/W2546672044","https://openalex.org/W2557283755","https://openalex.org/W2610751324","https://openalex.org/W2612526608","https://openalex.org/W2626778328","https://openalex.org/W2752172973","https://openalex.org/W2781528640","https://openalex.org/W2792196230","https://openalex.org/W2798649495","https://openalex.org/W2804241144","https://openalex.org/W2808963673","https://openalex.org/W2889284307","https://openalex.org/W2896457183","https://openalex.org/W2905135414","https://openalex.org/W2911347347","https://openalex.org/W2946504770","https://openalex.org/W2946741276","https://openalex.org/W2948978827","https://openalex.org/W2949388608","https://openalex.org/W2951147191","https://openalex.org/W2951559648","https://openalex.org/W2951882581","https://openalex.org/W2953289575","https://openalex.org/W2957204582","https://openalex.org/W2962781182","https://openalex.org/W2964121744","https://openalex.org/W2970641574","https://openalex.org/W2971681342","https://openalex.org/W2985009327","https://openalex.org/W2992897306","https://openalex.org/W2997574889","https://openalex.org/W2998702515","https://openalex.org/W3008672977","https://openalex.org/W3010144884","https://openalex.org/W3013447829","https://openalex.org/W3014295153","https://openalex.org/W3014705052","https://openalex.org/W3023371261","https://openalex.org/W3023459626","https://openalex.org/W3029269967","https://openalex.org/W3029701880","https://openalex.org/W3092962901","https://openalex.org/W3096174636","https://openalex.org/W3097013020","https://openalex.org/W3099734810","https://openalex.org/W3099883947","https://openalex.org/W3103177583","https://openalex.org/W3103543904","https://openalex.org/W3106020963","https://openalex.org/W3119752913","https://openalex.org/W3123375411","https://openalex.org/W3125024313","https://openalex.org/W3134767663","https://openalex.org/W3138971549","https://openalex.org/W3174250941","https://openalex.org/W4210880854","https://openalex.org/W4210956590","https://openalex.org/W4211193898","https://openalex.org/W4288253152"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"Entity":[0],"matching":[1],"(EM)":[2],"finds":[3],"data":[4,123],"instances":[5],"that":[6,45,70,154,194],"refer":[7],"to":[8,27,36,81],"the":[9,67,73,76,155,159,163,169,195,198],"same":[10],"real-world":[11],"entity.":[12],"Most":[13],"EM":[14],"solutions":[15,93,98,112,117,140,157,173,203],"perform":[16,141,205],"blocking":[17,39,82],"then":[18],"matching.":[19],"Many":[20],"works":[21,32,40],"have":[22,33],"applied":[23,34],"deep":[24],"learning":[25],"(DL)":[26],"matching,":[28],"but":[29],"far":[30],"fewer":[31],"DL":[35,53,80,92,129,166,200],"blocking.":[37],"These":[38,116],"are":[41,186],"also":[42],"limited":[43],"in":[44,78,113,128],"they":[46],"consider":[47],"only":[48],"a":[49,88,175,209],"simple":[50],"form":[51],"of":[52,56,75,91,99,146,197],"and":[54,102,124,168,182,185,201],"some":[55],"them":[57],"require":[58,120],"labeled":[59,121],"training":[60,122],"data.":[61,190],"In":[62],"this":[63,114],"paper,":[64],"we":[65,108,192],"develop":[66,109],"DeepBlocker":[68],"framework":[69],"significantly":[71],"advances":[72,127],"state":[74],"art":[77],"applying":[79],"for":[83,94,212],"EM.":[84],"We":[85,136,152],"first":[86],"define":[87],"large":[89],"space":[90],"blocking,":[95],"which":[96,139],"contains":[97],"varying":[100],"complexity":[101],"subsumes":[103],"most":[104],"previous":[105],"works.":[106],"Next,":[107],"eight":[110],"representative":[111],"space.":[115],"do":[118],"not":[119],"exploit":[125],"recent":[126],"(e.g.,":[130],"sequence":[131],"modeling,":[132],"transformer,":[133],"self":[134],"supervision).":[135],"empirically":[137],"determine":[138],"best":[142,156,164,170,199],"on":[143,180,188],"what":[144],"kind":[145],"datasets":[147],"(structured,":[148],"textual,":[149],"or":[150],"dirty).":[151],"show":[153,193],"(among":[158],"above":[160],"eight)":[161],"outperform":[162],"existing":[165,171],"solution":[167],"non-DL":[172,178,202],"(including":[174],"state-of-the-art":[176],"industrial":[177],"solution),":[179],"dirty":[181],"textual":[183],"data,":[184],"comparable":[187],"structured":[189],"Finally,":[191],"combination":[196],"can":[204],"even":[206],"better,":[207],"suggesting":[208],"new":[210],"venue":[211],"research.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":12},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":24},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":1}],"updated_date":"2026-08-09T07:27:16.801131","created_date":"2025-10-10T00:00:00"}