{"id":"https://openalex.org/W4281897885","doi":"https://doi.org/10.1145/3514221.3526147","title":"Hierarchical Entity Resolution using an Oracle","display_name":"Hierarchical Entity Resolution using an Oracle","publication_year":2022,"publication_date":"2022-06-10","ids":{"openalex":"https://openalex.org/W4281897885","doi":"https://doi.org/10.1145/3514221.3526147"},"language":"en","primary_location":{"id":"doi:10.1145/3514221.3526147","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3514221.3526147","pdf_url":null,"source":{"id":"https://openalex.org/S4363608845","display_name":"Proceedings of the 2022 International Conference on Management of Data","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Management of Data","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/11573/1640604","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038532934","display_name":"Sainyam Galhotra","orcid":"https://orcid.org/0000-0003-2529-4036"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]},{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sainyam Galhotra","raw_affiliation_strings":["University of Chicago, Chicago, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I40347166","https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063444742","display_name":"Donatella Firmani","orcid":"https://orcid.org/0000-0003-0358-3208"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Donatella Firmani","raw_affiliation_strings":["Sapienza University, Rome, UNK, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sapienza University, Rome, UNK, Italy","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110611660","display_name":"Barna Saha","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Barna Saha","raw_affiliation_strings":["University of California, San Diego, San Diego, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, San Diego, San Diego, CA, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","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 Chief Data Office, Bedminster, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT&T Chief Data Office, Bedminster, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"414","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":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/T10028","display_name":"Topic Modeling","score":0.9937999844551086,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9932000041007996,"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":0.832497239112854},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.826445460319519},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7668945789337158},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5498712658882141},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4940052628517151},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4889873266220093},{"id":"https://openalex.org/keywords/tree-structure","display_name":"Tree structure","score":0.4239165484905243},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.41141220927238464},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.30618029832839966},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23247161507606506},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08513477444648743}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.832497239112854},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.826445460319519},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7668945789337158},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5498712658882141},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4940052628517151},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4889873266220093},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.4239165484905243},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.41141220927238464},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.30618029832839966},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23247161507606506},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08513477444648743},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3514221.3526147","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3514221.3526147","pdf_url":null,"source":{"id":"https://openalex.org/S4363608845","display_name":"Proceedings of the 2022 International Conference on Management of Data","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Management of Data","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.uniroma1.it:11573/1640604","is_oa":true,"landing_page_url":"https://hdl.handle.net/11573/1640604","pdf_url":null,"source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:iris.uniroma1.it:11573/1640604","is_oa":true,"landing_page_url":"https://hdl.handle.net/11573/1640604","pdf_url":null,"source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.41999998688697815}],"awards":[{"id":"https://openalex.org/G3109196640","display_name":"HDR TRIPODS: Institute for Integrated Data Science: A Transdisciplinary Approach to Understanding Fundamental Trade-offs and Theoretical Foundations","funder_award_id":"1934846","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3385483125","display_name":"CIF: Small: New Directions in Clustering: Interactive Algorithms and Statistical Models","funder_award_id":"1909046","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4019597227","display_name":"Computing Innovation Fellows Project 2021","funder_award_id":"2127309","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G665357574","display_name":"CAREER: Efficient Fine-grained Algorithms","funder_award_id":"1652303","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8545607667","display_name":null,"funder_award_id":"HDR TRIPODS 1934846","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W1496255159","https://openalex.org/W1592764834","https://openalex.org/W1847921443","https://openalex.org/W1971077223","https://openalex.org/W1973264045","https://openalex.org/W1974554406","https://openalex.org/W1982876325","https://openalex.org/W2029344051","https://openalex.org/W2037055526","https://openalex.org/W2041439319","https://openalex.org/W2053653724","https://openalex.org/W2066640191","https://openalex.org/W2068737686","https://openalex.org/W2073471108","https://openalex.org/W2078109763","https://openalex.org/W2079970266","https://openalex.org/W2086288781","https://openalex.org/W2100132811","https://openalex.org/W2106675345","https://openalex.org/W2107480077","https://openalex.org/W2107966677","https://openalex.org/W2110922051","https://openalex.org/W2138605095","https://openalex.org/W2183076570","https://openalex.org/W2237063244","https://openalex.org/W2323506184","https://openalex.org/W2399361902","https://openalex.org/W2465217376","https://openalex.org/W2538903535","https://openalex.org/W2567739102","https://openalex.org/W2606287509","https://openalex.org/W2612964472","https://openalex.org/W2614094703","https://openalex.org/W2781953983","https://openalex.org/W2798649495","https://openalex.org/W2798691796","https://openalex.org/W2799106927","https://openalex.org/W2809189384","https://openalex.org/W2883559670","https://openalex.org/W2898956098","https://openalex.org/W2899053911","https://openalex.org/W2907607062","https://openalex.org/W2912254316","https://openalex.org/W2946504770","https://openalex.org/W2957204582","https://openalex.org/W2962814626","https://openalex.org/W2963587548","https://openalex.org/W2963737091","https://openalex.org/W2971681342","https://openalex.org/W2999905431","https://openalex.org/W3011807731","https://openalex.org/W3012733951","https://openalex.org/W3032015135","https://openalex.org/W3036762099","https://openalex.org/W3103177583","https://openalex.org/W3105298925","https://openalex.org/W3123856223","https://openalex.org/W3137039868","https://openalex.org/W3139172074","https://openalex.org/W4281897885","https://openalex.org/W4294645925","https://openalex.org/W4297971002","https://openalex.org/W6622620221","https://openalex.org/W6682171051","https://openalex.org/W6692522391"],"related_works":["https://openalex.org/W2093885745","https://openalex.org/W2351266481","https://openalex.org/W2132547887","https://openalex.org/W2516987005","https://openalex.org/W2907786475","https://openalex.org/W2963447120","https://openalex.org/W4289082820","https://openalex.org/W2092152400","https://openalex.org/W2372453241","https://openalex.org/W2071459461"],"abstract_inverted_index":{"In":[0,65,89],"many":[1],"applications,":[2],"entity":[3],"references":[4],"(i.e.,":[5],"records)":[6],"and":[7,24,43,58,103,109,129,162,173],"entities":[8,21],"need":[9],"to":[10,13,22,28,41,62,82,146,181],"be":[11],"organized":[12],"capture":[14],"diverse":[15],"relationships":[16,36,55],"like":[17],"type-subtype,":[18],"is-A":[19],"(mapping":[20,26],"types),":[23],"duplicate":[25],"records":[27,47,92,100,126],"entities)":[29],"relationships.":[30,111],"However,":[31],"automatic":[32],"identification":[33],"of":[34,46,53,79,115,150],"such":[35],"is":[37,56,166],"often":[38],"inaccurate":[39],"due":[40],"noise":[42,171],"heterogeneous":[44],"representation":[45],"across":[48],"sources.":[49],"Similarly,":[50],"manual":[51],"maintenance":[52],"these":[54,70],"infeasible":[57],"does":[59],"not":[60],"scale":[61,179],"large":[63],"datasets.":[64,183],"this":[66,90],"work,":[67],"we":[68,117],"circumvent":[69],"challenges":[71],"by":[72],"considering":[73],"weak":[74],"supervision":[75],"in":[76,95],"the":[77,131,148,155],"form":[78],"an":[80],"oracle":[81,121,151],"formulate":[83],"a":[84,96,138],"novel":[85],"hierarchical":[86,157],"ER":[87],"task.":[88],"setting,":[91],"are":[93],"clustered":[94],"tree-like":[97],"structure":[98],"containing":[99],"at":[101],"leaf-level":[102],"capturing":[104],"record-entity":[105],"(duplicate),":[106],"entity-type":[107],"(is-A)":[108],"subtype-supertype":[110],"For":[112],"effective":[113,167],"use":[114],"supervision,":[116],"leverage":[118],"triplet":[119],"comparison":[120],"queries":[122,152],"that":[123,141,164,176],"take":[124],"three":[125],"as":[127],"input":[128],"output":[130],"most":[132],"similar":[133],"pair(s).":[134],"We":[135,159],"develop":[136],"HierER,":[137],"querying":[139],"strategy":[140],"uses":[142],"record":[143],"pair":[144],"similarities":[145],"minimize":[147],"number":[149],"while":[153],"maximizing":[154],"identified":[156],"structure.":[158],"show":[160],"theoretically":[161],"empirically":[163,175],"HierER":[165,177],"under":[168],"different":[169],"similarity":[170],"models":[172],"demonstrate":[174],"can":[178],"up":[180],"million-size":[182]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}