{"id":"https://openalex.org/W4224288101","doi":"https://doi.org/10.1145/3524303","title":"Contextual Data Cleaning with Ontology Functional Dependencies","display_name":"Contextual Data Cleaning with Ontology Functional Dependencies","publication_year":2022,"publication_date":"2022-04-21","ids":{"openalex":"https://openalex.org/W4224288101","doi":"https://doi.org/10.1145/3524303"},"language":"en","primary_location":{"id":"doi:10.1145/3524303","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3524303","pdf_url":null,"source":{"id":"https://openalex.org/S110189822","display_name":"Journal of Data and Information Quality","issn_l":"1936-1955","issn":["1936-1955","1936-1963"],"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":"Journal of Data and Information Quality","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/A5100459073","display_name":"Zheng Zheng","orcid":"https://orcid.org/0000-0001-7922-9067"},"institutions":[{"id":"https://openalex.org/I98251732","display_name":"McMaster University","ror":"https://ror.org/02fa3aq29","country_code":"CA","type":"education","lineage":["https://openalex.org/I98251732"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Zheng Zheng","raw_affiliation_strings":["McMaster University, Ontario, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McMaster University, Ontario, Canada","institution_ids":["https://openalex.org/I98251732"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011940311","display_name":"Longtao Zheng","orcid":"https://orcid.org/0000-0002-7301-0862"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longtao Zheng","raw_affiliation_strings":["University of Science and Technology of China, Hefei, Anhui, P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, Anhui, P.R.China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083250721","display_name":"Morteza Alipourlangouri","orcid":"https://orcid.org/0000-0002-3185-766X"},"institutions":[{"id":"https://openalex.org/I98251732","display_name":"McMaster University","ror":"https://ror.org/02fa3aq29","country_code":"CA","type":"education","lineage":["https://openalex.org/I98251732"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Morteza Alipourlangouri","raw_affiliation_strings":["McMaster University, Ontario, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McMaster University, Ontario, Canada","institution_ids":["https://openalex.org/I98251732"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061267570","display_name":"Fei Chiang","orcid":"https://orcid.org/0000-0003-4128-8074"},"institutions":[{"id":"https://openalex.org/I98251732","display_name":"McMaster University","ror":"https://ror.org/02fa3aq29","country_code":"CA","type":"education","lineage":["https://openalex.org/I98251732"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Fei Chiang","raw_affiliation_strings":["McMaster University, Ontario, Canada"],"raw_orcid":"https://orcid.org/0000-0003-4128-8074","affiliations":[{"raw_affiliation_string":"McMaster University, Ontario, Canada","institution_ids":["https://openalex.org/I98251732"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049437648","display_name":"Lukasz Golab","orcid":"https://orcid.org/0000-0003-0632-7496"},"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":"Lukasz Golab","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035817202","display_name":"Jaroslaw Szlichta","orcid":"https://orcid.org/0000-0002-3382-2890"},"institutions":[{"id":"https://openalex.org/I39470171","display_name":"Ontario Tech University","ror":"https://ror.org/016zre027","country_code":"CA","type":"education","lineage":["https://openalex.org/I39470171"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jaroslaw Szlichta","raw_affiliation_strings":["Ontario Tech University, Oshawa, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ontario Tech University, Oshawa, ON, Canada","institution_ids":["https://openalex.org/I39470171"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079198051","display_name":"Sridevi Baskaran","orcid":null},"institutions":[{"id":"https://openalex.org/I98251732","display_name":"McMaster University","ror":"https://ror.org/02fa3aq29","country_code":"CA","type":"education","lineage":["https://openalex.org/I98251732"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sridevi Baskaran","raw_affiliation_strings":["McMaster University, Ontario, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"McMaster University, Ontario, Canada","institution_ids":["https://openalex.org/I98251732"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8448,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.74951966,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"14","issue":"3","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9865000247955322,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9782999753952026,"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/ontology","display_name":"Ontology","score":0.7685517072677612},{"id":"https://openalex.org/keywords/axiom","display_name":"Axiom","score":0.7481215000152588},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7112895250320435},{"id":"https://openalex.org/keywords/functional-dependency","display_name":"Functional dependency","score":0.672746479511261},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6331003904342651},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5675326585769653},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5335030555725098},{"id":"https://openalex.org/keywords/dependency-theory","display_name":"Dependency theory (database theory)","score":0.5106857419013977},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5035075545310974},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4084292948246002},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2971212863922119},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.25907015800476074},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19506990909576416}],"concepts":[{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.7685517072677612},{"id":"https://openalex.org/C167729594","wikidata":"https://www.wikidata.org/wiki/Q17736","display_name":"Axiom","level":2,"score":0.7481215000152588},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7112895250320435},{"id":"https://openalex.org/C26320393","wikidata":"https://www.wikidata.org/wiki/Q597053","display_name":"Functional dependency","level":3,"score":0.672746479511261},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6331003904342651},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5675326585769653},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5335030555725098},{"id":"https://openalex.org/C40683218","wikidata":"https://www.wikidata.org/wiki/Q5260625","display_name":"Dependency theory (database theory)","level":4,"score":0.5106857419013977},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5035075545310974},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4084292948246002},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2971212863922119},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.25907015800476074},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19506990909576416},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3524303","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3524303","pdf_url":null,"source":{"id":"https://openalex.org/S110189822","display_name":"Journal of Data and Information Quality","issn_l":"1936-1955","issn":["1936-1955","1936-1963"],"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":"Journal of Data and Information Quality","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1537955876","https://openalex.org/W1571341547","https://openalex.org/W1626378195","https://openalex.org/W1864010644","https://openalex.org/W1881756506","https://openalex.org/W1980185632","https://openalex.org/W1992479406","https://openalex.org/W2006637140","https://openalex.org/W2024443169","https://openalex.org/W2033079433","https://openalex.org/W2041442195","https://openalex.org/W2044469685","https://openalex.org/W2045566234","https://openalex.org/W2047745978","https://openalex.org/W2057773300","https://openalex.org/W2081186682","https://openalex.org/W2085480884","https://openalex.org/W2089206172","https://openalex.org/W2137095888","https://openalex.org/W2142472956","https://openalex.org/W2143668817","https://openalex.org/W2147805208","https://openalex.org/W2162449239","https://openalex.org/W2167333415","https://openalex.org/W2170712852","https://openalex.org/W2182148130","https://openalex.org/W2232417456","https://openalex.org/W2295468252","https://openalex.org/W2559785442","https://openalex.org/W2572059607","https://openalex.org/W2591700809","https://openalex.org/W2785119431","https://openalex.org/W2799022545","https://openalex.org/W2911001298","https://openalex.org/W2913731660","https://openalex.org/W2963803628","https://openalex.org/W2966581343","https://openalex.org/W3008589870","https://openalex.org/W3082197983","https://openalex.org/W3094989159","https://openalex.org/W3139384714","https://openalex.org/W4224288101","https://openalex.org/W6671960752","https://openalex.org/W6680244570"],"related_works":["https://openalex.org/W2392606101","https://openalex.org/W2072918301","https://openalex.org/W3162070149","https://openalex.org/W2489943546","https://openalex.org/W2362842011","https://openalex.org/W1034172250","https://openalex.org/W59130053","https://openalex.org/W1839867872","https://openalex.org/W2048090520","https://openalex.org/W2144130115"],"abstract_inverted_index":{"Functional":[0,33,153],"Dependencies":[1,34],"define":[2],"attribute":[3,39],"relationships":[4,40],"based":[5],"on":[6,129,151],"syntactic":[7],"equality,":[8],"and":[9,57,60,75,113,132],"when":[10],"used":[11],"in":[12,100,145],"data":[13,29,83,97,146],"cleaning,":[14],"they":[15],"erroneously":[16],"label":[17],"syntactically":[18],"different":[19],"but":[20],"semantically":[21],"equivalent":[22],"values":[23],"as":[24,42,96],"errors.":[25],"We":[26,48,65,122],"explore":[27],"dependency-based":[28],"cleaning":[30,147],"with":[31,79,115],"Ontology":[32],"(OFDs),":[35],"which":[36],"express":[37],"semantic":[38],"such":[41],"synonyms":[43],"defined":[44],"by":[45],"an":[46,68],"ontology.":[47],"study":[49,103],"the":[50,86,90,104,124,139],"theoretical":[51],"foundations":[52],"of":[53,106,120,126,141],"OFDs,":[54],"including":[55],"sound":[56],"complete":[58],"axioms":[59,87],"a":[61,111,118],"linear-time":[62],"inference":[63],"procedure.":[64],"then":[66],"propose":[67],"algorithm":[69],"for":[70],"discovering":[71],"OFDs":[72,95,135],"(exact":[73],"ones":[74,76],"that":[77,84,134,149],"hold":[78],"some":[80],"exceptions)":[81],"from":[82],"uses":[85],"to":[88,110,117],"prune":[89],"search":[91],"space.":[92],"Toward":[93],"enabling":[94],"quality":[98],"rules":[99],"practice,":[101],"we":[102],"problem":[105],"finding":[107],"minimal":[108],"repairs":[109],"relation":[112],"ontology":[114],"respect":[116],"set":[119],"OFDs.":[121],"demonstrate":[123],"effectiveness":[125],"our":[127],"techniques":[128,148],"real":[130],"datasets":[131],"show":[133],"can":[136],"significantly":[137],"reduce":[138],"number":[140],"false":[142],"positive":[143],"errors":[144],"rely":[150],"traditional":[152],"Dependencies.":[154]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
