{"id":"https://openalex.org/W2113415503","doi":"https://doi.org/10.14778/1687627.1687695","title":"Modeling and querying possible repairs in duplicate detection","display_name":"Modeling and querying possible repairs in duplicate detection","publication_year":2009,"publication_date":"2009-08-01","ids":{"openalex":"https://openalex.org/W2113415503","doi":"https://doi.org/10.14778/1687627.1687695","mag":"2113415503"},"language":"en","primary_location":{"id":"doi:10.14778/1687627.1687695","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1687627.1687695","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/A5047755628","display_name":"George Beskales","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"George Beskales","raw_affiliation_strings":["University of Waterloo","(University of Waterloo)"],"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"(University of Waterloo)","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046525599","display_name":"Mohamed A. Soliman","orcid":"https://orcid.org/0000-0001-8916-9133"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mohamed A. Soliman","raw_affiliation_strings":["University of Waterloo","(University of Waterloo)"],"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"(University of Waterloo)","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000141065","display_name":"Ihab F. Ilyas","orcid":"https://orcid.org/0000-0001-9052-9714"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ihab F. Ilyas","raw_affiliation_strings":["University of Waterloo","(University of Waterloo)"],"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"(University of Waterloo)","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112193907","display_name":"Shai Ben-David","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Shai Ben-David","raw_affiliation_strings":["University of Waterloo","(University of Waterloo)"],"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"(University of Waterloo)","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5047755628"],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":5.8323,"has_fulltext":false,"cited_by_count":57,"citation_normalized_percentile":{"value":0.96044205,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"2","issue":"1","first_page":"598","last_page":"609"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"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":0.9998000264167786,"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/T11106","display_name":"Data Management and Algorithms","score":0.9968000054359436,"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"}},{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9896000027656555,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7981522083282471},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7848390340805054},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6905674338340759},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.6594644784927368},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6303000450134277},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5739018321037292},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5598395466804504},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2613563537597656},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24543792009353638},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.24115610122680664}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7981522083282471},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7848390340805054},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6905674338340759},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.6594644784927368},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6303000450134277},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5739018321037292},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5598395466804504},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2613563537597656},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24543792009353638},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24115610122680664},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.14778/1687627.1687695","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1687627.1687695","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:CiteSeerX.psu:10.1.1.151.1860","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.151.1860","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.vldb.org/pvldb/2/vldb09-370.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.164.3000","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.164.3000","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.uwaterloo.ca/research/tr/2009/CS-2009-15B.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.180.8959","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.180.8959","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://db.uwaterloo.ca/%7Eilyas/papers/BeskalesVLDB2009.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.331.3480","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.331.3480","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://cs.uwaterloo.ca/research/tr/2009/CS-2009-15.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W60837915","https://openalex.org/W191253868","https://openalex.org/W1485156179","https://openalex.org/W1506073843","https://openalex.org/W1518784700","https://openalex.org/W1578663408","https://openalex.org/W1971784203","https://openalex.org/W1990391007","https://openalex.org/W2001341021","https://openalex.org/W2030724586","https://openalex.org/W2050071106","https://openalex.org/W2066406253","https://openalex.org/W2073471108","https://openalex.org/W2077518845","https://openalex.org/W2078686663","https://openalex.org/W2106582507","https://openalex.org/W2108991785","https://openalex.org/W2129598390","https://openalex.org/W2131687179","https://openalex.org/W2133676910","https://openalex.org/W2148019918","https://openalex.org/W2149098716","https://openalex.org/W2163382775","https://openalex.org/W2166994031","https://openalex.org/W2167396179","https://openalex.org/W2319660501","https://openalex.org/W3092497216","https://openalex.org/W6770641979"],"related_works":["https://openalex.org/W2051058708","https://openalex.org/W154868527","https://openalex.org/W1494268238","https://openalex.org/W1983207144","https://openalex.org/W2490706771","https://openalex.org/W1976468483","https://openalex.org/W2480116122","https://openalex.org/W1516574938","https://openalex.org/W2563912921","https://openalex.org/W3151146928"],"abstract_inverted_index":{"One":[0],"of":[1,11,24,33,76,104,125,149,154,168],"the":[2,9,25,31,34,39,57,123,152,163,166],"most":[3],"prominent":[4],"data":[5,60,93],"quality":[6],"problems":[7],"is":[8],"existence":[10],"duplicate":[12,15,35,78,89,105],"records.":[13],"Current":[14],"elimination":[16],"procedures":[17,91],"usually":[18],"produce":[19],"one":[20,62],"clean":[21,64],"instance":[22,65],"(repair)":[23],"input":[26,58],"data,":[27],"by":[28],"carefully":[29],"choosing":[30],"parameters":[32],"detection":[36,90,106],"algorithms.":[37],"Finding":[38],"right":[40],"parameter":[41,131],"settings":[42,51],"can":[43],"be":[44],"hard,":[45],"and":[46,74,144,165],"in":[47,68,80,171],"many":[48],"cases,":[49],"perfect":[50],"do":[52],"not":[53],"exist.":[54],"Furthermore,":[55],"replacing":[56],"dirty":[59],"with":[61,96],"possible":[63,77,126,155],"may":[66],"result":[67],"unrecoverable":[69],"errors,":[70],"for":[71],"example,":[72],"identification":[73],"merging":[75],"records":[79],"health":[81],"care":[82],"systems.":[83],"In":[84],"this":[85],"paper,":[86],"we":[87],"treat":[88],"as":[92],"processing":[94],"tasks":[95],"uncertain":[97],"outcomes.":[98],"We":[99,114,133,157],"concentrate":[100],"on":[101,111,151],"a":[102,116],"family":[103],"algorithms":[107],"that":[108,120],"are":[109],"based":[110],"parameterized":[112],"clustering.":[113],"propose":[115],"novel":[117],"uncertainty":[118],"model":[119],"compactly":[121],"encodes":[122],"space":[124],"repairs":[127],"corresponding":[128],"to":[129,136,145],"different":[130,172],"settings.":[132],"show":[134],"how":[135],"efficiently":[137],"support":[138],"relational":[139],"queries":[140,150],"under":[141],"our":[142,169],"model,":[143],"allow":[146],"new":[147],"types":[148],"set":[153],"repairs.":[156],"give":[158],"an":[159],"experimental":[160],"study":[161],"illustrating":[162],"scalability":[164],"efficiency":[167],"techniques":[170],"configurations.":[173]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}