{"id":"https://openalex.org/W2008641248","doi":"https://doi.org/10.1109/icde.2010.5447744","title":"ProbClean: A probabilistic duplicate detection system","display_name":"ProbClean: A probabilistic duplicate detection system","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2008641248","doi":"https://doi.org/10.1109/icde.2010.5447744","mag":"2008641248"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2010.5447744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2010.5447744","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE 26th International Conference on Data Engineering (ICDE 2010)","raw_type":"proceedings-article"},"type":"conference-paper","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":false,"raw_author_name":"George Beskales","raw_affiliation_strings":["School of Computer Science, University of Waterloo, Canada","School of Computer Science, University of Waterloo, , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"School of Computer Science, University of Waterloo, , Canada","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":["School of Computer Science, University of Waterloo, Canada","School of Computer Science, University of Waterloo, , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"School of Computer Science, University of Waterloo, , Canada","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":["School of Computer Science, University of Waterloo, Canada","School of Computer Science, University of Waterloo, , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"School of Computer Science, University of Waterloo, , Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","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":["School of Computer Science, University of Waterloo, Canada","School of Computer Science, University of Waterloo, , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"School of Computer Science, University of Waterloo, , Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108104844","display_name":"Yubin Kim","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":"Yubin Kim","raw_affiliation_strings":["School of Computer Science, University of Waterloo, Canada","School of Computer Science, University of Waterloo, , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"School of Computer Science, University of Waterloo, , Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1193","last_page":"1196"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9976999759674072,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9950000047683716,"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":0.772590160369873},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7548154592514038},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.626517653465271},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5811285376548767},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4612480700016022},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.451200395822525},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.43482735753059387},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2336399257183075}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.772590160369873},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7548154592514038},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.626517653465271},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5811285376548767},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4612480700016022},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.451200395822525},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.43482735753059387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2336399257183075},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icde.2010.5447744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2010.5447744","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE 26th International Conference on Data Engineering (ICDE 2010)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1971784203","https://openalex.org/W2078686663","https://openalex.org/W2113415503","https://openalex.org/W2319660501"],"related_works":["https://openalex.org/W2943623134","https://openalex.org/W2494523064","https://openalex.org/W2588219639","https://openalex.org/W2215759665","https://openalex.org/W2030292806","https://openalex.org/W2960358116","https://openalex.org/W4287727129","https://openalex.org/W3041172967","https://openalex.org/W2749065928","https://openalex.org/W2147155098"],"abstract_inverted_index":{"One":[0],"of":[1,11,24,33,83,100,105],"the":[2,9,25,31,34,39,81],"most":[3],"prominent":[4],"data":[5,15,66],"quality":[6],"problems":[7],"is":[8],"existence":[10],"duplicate":[12,35,62],"records.":[13],"Current":[14],"cleaning":[16],"systems":[17],"usually":[18],"produce":[19],"one":[20],"clean":[21],"instance":[22],"(repair)":[23],"input":[26],"data,":[27],"by":[28],"carefully":[29],"choosing":[30],"parameters":[32],"detection":[36,63],"algorithms.":[37],"Finding":[38],"right":[40],"parameter":[41,89],"settings":[42,51],"can":[43],"be":[44],"hard,":[45],"and":[46,96],"in":[47],"many":[48],"cases,":[49],"perfect":[50],"do":[52],"not":[53],"exist.":[54],"We":[55,72],"propose":[56],"ProbClean,":[57],"a":[58,74,103],"system":[59],"that":[60,78],"treats":[61],"procedures":[64],"as":[65],"processing":[67],"tasks":[68],"with":[69],"uncertain":[70],"outcomes.":[71],"use":[73],"novel":[75],"uncertainty":[76],"model":[77],"compactly":[79],"encodes":[80],"space":[82],"possible":[84,106],"repairs":[85],"corresponding":[86],"to":[87],"different":[88],"settings.":[90],"ProbClean":[91],"efficiently":[92],"supports":[93],"relational":[94],"queries":[95,101],"allows":[97],"new":[98],"types":[99],"against":[102],"set":[104],"repairs.":[107]},"counts_by_year":[{"year":2020,"cited_by_count":4},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
