{"id":"https://openalex.org/W3045786285","doi":"https://doi.org/10.1109/tkde.2020.3012472","title":"A Hybrid Data Cleaning Framework Using Markov Logic Networks","display_name":"A Hybrid Data Cleaning Framework Using Markov Logic Networks","publication_year":2020,"publication_date":"2020-07-28","ids":{"openalex":"https://openalex.org/W3045786285","doi":"https://doi.org/10.1109/tkde.2020.3012472","mag":"3045786285"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2020.3012472","doi":"https://doi.org/10.1109/tkde.2020.3012472","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2020.3012472","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-a","cwts-core","dongbi-a","fnege-3","jufo-3","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1903.05826","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088891882","display_name":"Congcong Ge","orcid":"https://orcid.org/0009-0001-4460-2738","observed_orcids":["https://orcid.org/0009-0001-4460-2738"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Congcong Ge","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006238145","display_name":"Yunjun Gao","orcid":"https://orcid.org/0000-0003-3816-8450","observed_orcids":["https://orcid.org/0000-0003-3816-8450"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunjun Gao","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0003-3816-8450","affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014150958","display_name":"Xiaoye Miao","orcid":"https://orcid.org/0000-0002-8632-1539","observed_orcids":["https://orcid.org/0000-0002-8632-1539"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoye Miao","raw_affiliation_strings":["Center for Data Science, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0002-8632-1539","affiliations":[{"raw_affiliation_string":"Center for Data Science, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100757927","display_name":"Bin Yao","orcid":"https://orcid.org/0000-0002-6478-4209","observed_orcids":["https://orcid.org/0000-0002-6478-4209"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Yao","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6478-4209","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049707744","display_name":"Haobo Wang","orcid":"https://orcid.org/0000-0001-8586-3048","observed_orcids":["https://orcid.org/0000-0001-8586-3048"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haobo Wang","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0001-8586-3048","affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2045,"currency":"USD","value_usd":2045},"apc_paid":null,"fwci":2.8791,"has_fulltext":true,"cited_by_count":48,"citation_normalized_percentile":{"value":0.91686931,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":"34","issue":"5","first_page":"2048","last_page":"2062"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9990000128746033,"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"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.00019999999494757503,"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"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.00019999999494757503,"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/data-cleaning","display_name":"data cleaning","score":0.9940000176429749},{"id":"https://openalex.org/keywords/markov-logic-networks","display_name":"Markov logic networks","score":0.9890000224113464},{"id":"https://openalex.org/keywords/dirty-data","display_name":"dirty data","score":0.7670000195503235},{"id":"https://openalex.org/keywords/integrity-constraints","display_name":"integrity constraints","score":0.8830000162124634},{"id":"https://openalex.org/keywords/rule-learning","display_name":"rule induction","score":0.8619999885559082},{"id":"https://openalex.org/keywords/data-versioning","display_name":"data versioning","score":0.6039999723434448},{"id":"https://openalex.org/keywords/index-structures","display_name":"index structures","score":0.6790000200271606},{"id":"https://openalex.org/keywords/reliability-score","display_name":"reliability score","score":0.9559999704360962}],"concepts":[{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.8055874109268188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5390156507492065},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4302389919757843},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42705416679382324},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3721303343772888},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.31821343302726746},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2783176898956299},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.2195521593093872},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10112947225570679}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tkde.2020.3012472","doi":"https://doi.org/10.1109/tkde.2020.3012472","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2020.3012472","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-a","cwts-core","dongbi-a","fnege-3","jufo-3","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1903.05826","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.05826","pdf_url":"https://arxiv.org/pdf/1903.05826","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.1903.05826","doi":"https://doi.org/10.48550/arxiv.1903.05826","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1903.05826","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1903.05826","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.05826","pdf_url":"https://arxiv.org/pdf/1903.05826","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1828425977","display_name":null,"funder_award_id":"973 Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2462854349","display_name":null,"funder_award_id":"U1609217","funder_id":"https://openalex.org/F4320334064","funder_display_name":"National Natural Science Foundation of China-Zhejiang Joint Fund for the Integration of Industrialization and Informatization"},{"id":"https://openalex.org/G2937796669","display_name":null,"funder_award_id":"2018YFB1004003","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G3503326317","display_name":null,"funder_award_id":"2015CB352502","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5047629933","display_name":null,"funder_award_id":"U1609217","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5916212369","display_name":"\u53cdTop-k\u7a7a\u95f4\u5173\u952e\u5b57\u67e5\u8be2\u53ef\u7528\u6027\u7814\u7a76","funder_award_id":"61972338","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G628069048","display_name":null,"funder_award_id":"61902343","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G839750106","display_name":null,"funder_award_id":"2015CB352502","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8438808684","display_name":null,"funder_award_id":"61522208","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334064","display_name":"National Natural Science Foundation of China-Zhejiang Joint Fund for the Integration of Industrialization and Informatization","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3045786285.pdf","grobid_xml":"https://content.openalex.org/works/W3045786285.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W790941020","https://openalex.org/W1610496399","https://openalex.org/W1626378195","https://openalex.org/W1964786778","https://openalex.org/W1976732638","https://openalex.org/W1992479406","https://openalex.org/W1997945384","https://openalex.org/W2041442195","https://openalex.org/W2044469685","https://openalex.org/W2046298800","https://openalex.org/W2047745978","https://openalex.org/W2056748234","https://openalex.org/W2068376489","https://openalex.org/W2081186682","https://openalex.org/W2089206172","https://openalex.org/W2099637074","https://openalex.org/W2112840274","https://openalex.org/W2135209143","https://openalex.org/W2136709660","https://openalex.org/W2137775416","https://openalex.org/W2153531471","https://openalex.org/W2159100004","https://openalex.org/W2164187405","https://openalex.org/W2167333415","https://openalex.org/W2170712852","https://openalex.org/W2171332293","https://openalex.org/W2213275763","https://openalex.org/W2295468252","https://openalex.org/W2437617937","https://openalex.org/W2548122763","https://openalex.org/W2591700809","https://openalex.org/W2752463530","https://openalex.org/W2804988694","https://openalex.org/W2808345493","https://openalex.org/W2929941791","https://openalex.org/W3000214033","https://openalex.org/W3023049136","https://openalex.org/W4300246663"],"related_works":["https://openalex.org/W3175358996","https://openalex.org/W2970182055","https://openalex.org/W7214264788","https://openalex.org/W7098052692","https://openalex.org/W4401171667","https://openalex.org/W3216138617","https://openalex.org/W3215947082","https://openalex.org/W2386309059","https://openalex.org/W2075268020","https://openalex.org/W4414232323"],"abstract_inverted_index":{"With":[0],"the":[1,19,59,71,100,104,125,148],"increase":[2],"of":[3,12,18,42,53,64,78],"dirty":[4],"data,":[5],"data":[6,13,37,68,96,106,119,130],"cleaning":[7,23,38,101,107],"turns":[8],"into":[9],"a":[10,34,76,88,111,133],"crux":[11],"analysis.":[14],"The":[15],"accuracy":[16],"limitation":[17],"existing":[20],"integrity":[21,61],"constraints-based":[22],"approaches":[24],"results":[25,140],"from":[26],"insufficient":[27,60],"rules.":[28],"In":[29,70,103],"this":[30],"paper,":[31],"we":[32],"present":[33],"novel":[35,134],"hybrid":[36],"framework":[39],"on":[40,141],"top":[41],"Markov":[43],"logic":[44],"networks":[45],"(MLNs),":[46],"termed":[47],"as${\\sf":[48],"MLNClean}$,":[49],"which":[50],"is":[51],"capable":[52],"learning":[54],"instantiated":[55,80],"rules":[56,81],"to":[57,83,93],"supplement":[58],"constraints.${\\sf":[62],"MLNClean}$consists":[63],"two":[65],"steps,":[66],"i.e.,pre-processingandtwo-stage":[67],"cleaning.":[69],"pre-processing":[72],"step,${\\sf":[73,108],"MLNClean}$first":[74,109],"infers":[75],"set":[77],"probable":[79],"according":[82],"MLNs":[84],"and":[85,98,122,144],"then":[86],"builds":[87],"two-layer":[89],"MLN":[90],"index":[91],"structure":[92],"generate":[94],"multiple":[95],"versions":[97],"facilitate":[99],"process.":[102],"two-stage":[105],"presents":[110],"concept":[112,135],"ofreliability":[113],"scoreto":[114],"clean":[115],"errors":[116],"within":[117],"each":[118],"version":[120,131],"separately,":[121],"afterward":[123],"eliminates":[124],"conflict":[126],"values":[127],"among":[128],"different":[129],"using":[132],"offusion":[136],"score.":[137],"Considerable":[138],"experimental":[139],"both":[142],"real":[143],"synthetic":[145],"scenarios":[146],"demonstrate":[147],"effectiveness":[149],"of${\\sf":[150],"MLNClean}$in":[151],"practice.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2020-08-03T00:00:00"}