{"id":"https://openalex.org/W3191403450","doi":"https://doi.org/10.24963/ijcai.2021/488","title":"SPADE: A Semi-supervised Probabilistic Approach for Detecting Errors in Tables","display_name":"SPADE: A Semi-supervised Probabilistic Approach for Detecting Errors in Tables","publication_year":2021,"publication_date":"2021-08-01","ids":{"openalex":"https://openalex.org/W3191403450","doi":"https://doi.org/10.24963/ijcai.2021/488","mag":"3191403450"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2021/488","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/488","pdf_url":"https://www.ijcai.org/proceedings/2021/0488.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2021/0488.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046030806","display_name":"Tam Minh Pham","orcid":"https://orcid.org/0000-0002-5899-9537"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Minh Pham","raw_affiliation_strings":["Information Sciences Institute, University of Southern California"],"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089542402","display_name":"Craig A. Knoblock","orcid":"https://orcid.org/0000-0002-6371-4807"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Craig A. Knoblock","raw_affiliation_strings":["Information Sciences Institute, University of Southern California"],"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102861481","display_name":"Muhao Chen","orcid":"https://orcid.org/0000-0003-0118-3147"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Muhao Chen","raw_affiliation_strings":["Information Sciences Institute, University of Southern California"],"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034928563","display_name":"B\u00ecnh D\u01b0\u01a1ng V\u0169","orcid":"https://orcid.org/0000-0002-6759-4443"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Binh Vu","raw_affiliation_strings":["Information Sciences Institute, University of Southern California"],"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073443117","display_name":"Jay Pujara","orcid":"https://orcid.org/0000-0001-6921-1744"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jay Pujara","raw_affiliation_strings":["Information Sciences Institute, University of Southern California"],"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5046030806"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.5382,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.69188337,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3543","last_page":"3551"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994000196456909,"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":0.9994000196456909,"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/T10260","display_name":"Software Engineering Research","score":0.9961000084877014,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9952999949455261,"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":0.784561276435852},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.742692232131958},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6663329005241394},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6415591835975647},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5526448488235474},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.4973583519458771},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.45772773027420044},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42564791440963745},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.4216420650482178},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41101229190826416},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32704800367355347},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.14995765686035156}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.784561276435852},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.742692232131958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6663329005241394},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6415591835975647},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5526448488235474},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4973583519458771},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.45772773027420044},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42564791440963745},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.4216420650482178},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41101229190826416},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32704800367355347},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.14995765686035156},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2021/488","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/488","pdf_url":"https://www.ijcai.org/proceedings/2021/0488.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2021/488","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/488","pdf_url":"https://www.ijcai.org/proceedings/2021/0488.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7452299184","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G8998121839","display_name":null,"funder_award_id":"911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3191403450.pdf","grobid_xml":"https://content.openalex.org/works/W3191403450.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1992479406","https://openalex.org/W2012878613","https://openalex.org/W2101234009","https://openalex.org/W2295598076","https://openalex.org/W2298871042","https://openalex.org/W2493916176","https://openalex.org/W2544486974","https://openalex.org/W2548122763","https://openalex.org/W2560438049","https://openalex.org/W2591700809","https://openalex.org/W2911964244","https://openalex.org/W2949244208","https://openalex.org/W2952738808","https://openalex.org/W2963572185","https://openalex.org/W2987471611","https://openalex.org/W3008684766","https://openalex.org/W3102476541","https://openalex.org/W3205420294","https://openalex.org/W4288357592"],"related_works":["https://openalex.org/W4312414840","https://openalex.org/W2794908468","https://openalex.org/W4206276646","https://openalex.org/W2943467239","https://openalex.org/W1571801203","https://openalex.org/W101422005","https://openalex.org/W192740413","https://openalex.org/W3004135598","https://openalex.org/W2952937263","https://openalex.org/W2131153761"],"abstract_inverted_index":{"Error":[0],"detection":[1,26],"is":[2],"one":[3],"of":[4,31,128],"the":[5,50,75,84,140],"most":[6],"important":[7],"steps":[8],"in":[9,24],"data":[10,33,103],"cleaning":[11],"and":[12,89,133],"usually":[13,44],"requires":[14],"extensive":[15],"human":[16],"interaction":[17],"to":[18,46,48,79,95,106,116],"ensure":[19],"quality.":[20],"Existing":[21],"supervised":[22],"methods":[23,36],"error":[25,64],"require":[27],"a":[28,58,68,101,108,112,135],"significant":[29],"amount":[30],"training":[32,111],"while":[34],"unsupervised":[35],"rely":[37],"on":[38,83],"fixed":[39],"inductive":[40],"biases,":[41],"which":[42,92],"are":[43,93],"hard":[45],"generalize,":[47],"solve":[49],"problem.":[51],"In":[52,120],"this":[53],"paper,":[54],"we":[55],"present":[56],"SPADE,":[57],"novel":[59,69],"semi-supervised":[60],"probabilistic":[61,70],"approach":[62],"for":[63],"detection.":[65],"SPADE":[66,99,123],"introduces":[67],"active":[71],"learning":[72,114],"model,":[73],"where":[74],"system":[76],"suggests":[77],"examples":[78],"be":[80],"labeled":[81],"based":[82],"agreements":[85],"between":[86],"user":[87],"labels":[88],"indicative":[90],"signals,":[91],"designed":[94],"capture":[96],"potential":[97],"errors.":[98,119],"uses":[100],"two-phase":[102],"augmentation":[104],"process":[105],"enrich":[107],"dataset":[109],"before":[110],"deep":[113],"classifier":[115],"detect":[117],"unlabeled":[118],"our":[121],"evaluation,":[122],"achieves":[124],"an":[125],"average":[126],"F1-score":[127],"0.91":[129],"over":[130],"five":[131],"datasets":[132],"yields":[134],"10%":[136],"improvement":[137],"compared":[138],"with":[139],"state-of-the-art":[141],"systems.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}