{"id":"https://openalex.org/W4283312893","doi":"https://doi.org/10.14778/3523210.3523226","title":"Entity resolution on-demand","display_name":"Entity resolution on-demand","publication_year":2022,"publication_date":"2022-03-01","ids":{"openalex":"https://openalex.org/W4283312893","doi":"https://doi.org/10.14778/3523210.3523226"},"language":"en","primary_location":{"id":"doi:10.14778/3523210.3523226","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3523210.3523226","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":true,"oa_status":"green","oa_url":"http://hdl.handle.net/11380/1278078","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047630333","display_name":"Giovanni Simonini","orcid":"https://orcid.org/0000-0002-3466-509X"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Giovanni Simonini","raw_affiliation_strings":["University of Modena and Reggio Emilia, Italy"],"affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia, Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061991280","display_name":"Luca Zecchini","orcid":"https://orcid.org/0000-0002-4856-0838"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luca Zecchini","raw_affiliation_strings":["University of Modena and Reggio Emilia, Italy"],"affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia, Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037830808","display_name":"Sonia Bergamaschi","orcid":"https://orcid.org/0000-0001-8087-6587"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sonia Bergamaschi","raw_affiliation_strings":["University of Modena and Reggio Emilia, Italy"],"affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia, Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053028480","display_name":"Felix Naumann","orcid":"https://orcid.org/0000-0002-4483-1389"},"institutions":[{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Naumann","raw_affiliation_strings":["University of Potsdam, Germany"],"affiliations":[{"raw_affiliation_string":"University of Potsdam, Germany","institution_ids":["https://openalex.org/I176453806"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5047630333"],"corresponding_institution_ids":["https://openalex.org/I122346577"],"apc_list":null,"apc_paid":null,"fwci":3.2734,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.92427041,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"15","issue":"7","first_page":"1506","last_page":"1518"},"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":0.9787999987602234,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9722999930381775,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.832658052444458},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.6963224411010742},{"id":"https://openalex.org/keywords/predicate","display_name":"Predicate (mathematical logic)","score":0.5005347728729248},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.4769372344017029},{"id":"https://openalex.org/keywords/data-cleansing","display_name":"Data cleansing","score":0.4662569761276245},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.430345356464386},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3887367844581604},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.30523279309272766},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.2490999698638916},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09072750806808472},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.08707967400550842}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.832658052444458},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.6963224411010742},{"id":"https://openalex.org/C140146324","wikidata":"https://www.wikidata.org/wiki/Q1144319","display_name":"Predicate (mathematical logic)","level":2,"score":0.5005347728729248},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.4769372344017029},{"id":"https://openalex.org/C42199009","wikidata":"https://www.wikidata.org/wiki/Q1172378","display_name":"Data cleansing","level":4,"score":0.4662569761276245},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.430345356464386},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3887367844581604},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.30523279309272766},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.2490999698638916},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09072750806808472},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.08707967400550842},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.14778/3523210.3523226","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3523210.3523226","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"},{"id":"pmh:oai:iris.unimore.it:11380/1278078","is_oa":true,"landing_page_url":"http://hdl.handle.net/11380/1278078","pdf_url":null,"source":{"id":"https://openalex.org/S4306400718","display_name":"IRIS UNIMORE (University of Modena and Reggio Emilia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122346577","host_organization_name":"University of Modena and Reggio Emilia","host_organization_lineage":["https://openalex.org/I122346577"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:kobv.de-opus4-uni-potsdam:65088","is_oa":true,"landing_page_url":"https://publishup.uni-potsdam.de/frontdoor/index/index/docId/65088","pdf_url":null,"source":{"id":"https://openalex.org/S4306400594","display_name":"publish.UP (University of Potsdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I176453806","host_organization_name":"University of Potsdam","host_organization_lineage":["https://openalex.org/I176453806"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:iris.unimore.it:11380/1278078","is_oa":true,"landing_page_url":"http://hdl.handle.net/11380/1278078","pdf_url":null,"source":{"id":"https://openalex.org/S4306400718","display_name":"IRIS UNIMORE (University of Modena and Reggio Emilia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122346577","host_organization_name":"University of Modena and Reggio Emilia","host_organization_lineage":["https://openalex.org/I122346577"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2031250218","https://openalex.org/W2065758089","https://openalex.org/W2073471108","https://openalex.org/W2108087318","https://openalex.org/W2123561513","https://openalex.org/W2146635036","https://openalex.org/W2168440643","https://openalex.org/W2220488081","https://openalex.org/W2237063244","https://openalex.org/W2399361902","https://openalex.org/W2546466160","https://openalex.org/W2750620035","https://openalex.org/W2798649495","https://openalex.org/W2805578827","https://openalex.org/W2946741276","https://openalex.org/W2962856906","https://openalex.org/W2970992672","https://openalex.org/W3007475739","https://openalex.org/W3014705052","https://openalex.org/W3029269967","https://openalex.org/W3029701880","https://openalex.org/W3032015135","https://openalex.org/W3045211065","https://openalex.org/W3106020963","https://openalex.org/W3123375411","https://openalex.org/W3125024313","https://openalex.org/W3137039868","https://openalex.org/W3155638005","https://openalex.org/W3176502563","https://openalex.org/W3197468999"],"related_works":["https://openalex.org/W2369673098","https://openalex.org/W2386315983","https://openalex.org/W2158198137","https://openalex.org/W2357241418","https://openalex.org/W2150276710","https://openalex.org/W2086064646","https://openalex.org/W2119135658","https://openalex.org/W2115485936","https://openalex.org/W2347219288","https://openalex.org/W2356606971"],"abstract_inverted_index":{"Entity":[0],"Resolution":[1],"(ER)":[2],"aims":[3],"to":[4,11,64,67,90,116,138],"identify":[5],"and":[6,94,159,179],"merge":[7],"records":[8],"that":[9],"refer":[10],"the":[12,26,43,69,79,96,140,181],"same":[13],"real-world":[14,187],"entity.":[15],"ER":[16],"is":[17],"typically":[18],"employed":[19],"as":[20,128],"an":[21,150],"expensive":[22],"cleaning":[23,78,141],"step":[24],"on":[25,42,121,133,143,185],"entire":[27],"data":[28,86,92,123],"before":[29],"consuming":[30],"it.":[31],"Yet,":[32],"determining":[33],"which":[34,46],"entities":[35,70],"are":[36],"useful":[37],"once":[38],"cleaned":[39,134],"depends":[40],"solely":[41],"user's":[44],"application,":[45],"may":[47],"need":[48],"only":[49],"a":[50,99,114,147,163,168],"fraction":[51],"of":[52,71,104,166,171,183],"them.":[53],"For":[54,162],"instance,":[55],"when":[56,84],"dealing":[57],"with":[58],"Web":[59],"data,":[60],"we":[61,88],"would":[62],"like":[63],"be":[65,174],"able":[66],"filter":[68],"interest":[72],"gathered":[73],"from":[74],"multiple":[75],"sources":[76],"without":[77],"entire,":[80],"continuously-growing":[81],"data.":[82,135],"Similarly,":[83],"querying":[85],"lakes,":[87],"want":[89],"transform":[91],"on-demand":[93],"return":[95],"results":[97,127],"in":[98],"timely":[100],"manner---a":[101],"fundamental":[102],"requirement":[103],"ELT":[105],"(":[106],"Extract-Load-Transform":[107],")":[108],"pipelines.":[109],"We":[110,176],"propose":[111],"BrewER":[112,136,184],",":[113],"framework":[115],"evaluate":[117,178],"SQL":[118],"SP":[119],"queries":[120],"dirty":[122],"while":[124],"progressively":[125],"returning":[126],"if":[129],"they":[130],"were":[131],"issued":[132],"tries":[137],"focus":[139],"effort":[142],"one":[144],"entity":[145],"at":[146],"time,":[148],"following":[149],"ORDER":[151],"BY":[152],"predicate.":[153],"Thus,":[154],"it":[155],"inherently":[156],"supports":[157],"top-k":[158],"stop-and-resume":[160],"execution.":[161],"wide":[164],"range":[165],"applications,":[167],"significant":[169],"amount":[170],"resources":[172],"can":[173],"saved.":[175],"exhaustively":[177],"show":[180],"efficacy":[182],"four":[186],"datasets.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
