{"id":"https://openalex.org/W4391094754","doi":"https://doi.org/10.1109/bigdata59044.2023.10386632","title":"Detecting Semantic Errors in Tables using Textual Evidence","display_name":"Detecting Semantic Errors in Tables using Textual Evidence","publication_year":2023,"publication_date":"2023-12-15","ids":{"openalex":"https://openalex.org/W4391094754","doi":"https://doi.org/10.1109/bigdata59044.2023.10386632"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata59044.2023.10386632","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata59044.2023.10386632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-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/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":["University of Southern California,Information Sciences Institute,Los Angeles,CA","Information Sciences Institute, University of Southern California, Los Angeles, CA"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Information Sciences Institute,Los Angeles,CA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Information Sciences Institute, University of Southern California, Los Angeles, CA","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":["University of Southern California,Information Sciences Institute,Los Angeles,CA","Information Sciences Institute, University of Southern California, Los Angeles, CA"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Information Sciences Institute,Los Angeles,CA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Information Sciences Institute, University of Southern California, Los Angeles, CA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","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":["University of Southern California,Information Sciences Institute,Los Angeles,CA","Information Sciences Institute, University of Southern California, Los Angeles, CA"],"affiliations":[{"raw_affiliation_string":"University of Southern California,Information Sciences Institute,Los Angeles,CA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Information Sciences Institute, University of Southern California, Los Angeles, CA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046030806"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.2545,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.62868088,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"33","issue":null,"first_page":"292","last_page":"303"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"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":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","score":0.9977999925613403,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9855999946594238,"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":0.9034843444824219},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.7064213156700134},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6633665561676025},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5752608776092529},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5319694876670837},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5009684562683105},{"id":"https://openalex.org/keywords/semantic-computing","display_name":"Semantic computing","score":0.4804674983024597},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4803786873817444},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.465913325548172},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.4420279264450073},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4264300465583801},{"id":"https://openalex.org/keywords/semantic-data-model","display_name":"Semantic data model","score":0.412395179271698},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.41118475794792175},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.4111127257347107},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.26884526014328003},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.1494775414466858},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12488067150115967},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.11975753307342529},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10887607932090759}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9034843444824219},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7064213156700134},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6633665561676025},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5752608776092529},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5319694876670837},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5009684562683105},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.4804674983024597},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4803786873817444},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.465913325548172},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.4420279264450073},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4264300465583801},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.412395179271698},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.41118475794792175},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.4111127257347107},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26884526014328003},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.1494775414466858},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12488067150115967},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.11975753307342529},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10887607932090759},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata59044.2023.10386632","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/bigdata59044.2023.10386632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5199999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1521736627","https://openalex.org/W1992479406","https://openalex.org/W2016048023","https://openalex.org/W2034267313","https://openalex.org/W2046298800","https://openalex.org/W2298871042","https://openalex.org/W2342096063","https://openalex.org/W2474573819","https://openalex.org/W2544486974","https://openalex.org/W2751448157","https://openalex.org/W2798323405","https://openalex.org/W2896457183","https://openalex.org/W2929941791","https://openalex.org/W2943955885","https://openalex.org/W2948145720","https://openalex.org/W2950336186","https://openalex.org/W2963899988","https://openalex.org/W2964068236","https://openalex.org/W2970476646","https://openalex.org/W2971822538","https://openalex.org/W2987471611","https://openalex.org/W3011411500","https://openalex.org/W3027879771","https://openalex.org/W3034999214","https://openalex.org/W3035140194","https://openalex.org/W3035275890","https://openalex.org/W3082197983","https://openalex.org/W3098495697","https://openalex.org/W3099655892","https://openalex.org/W3099700870","https://openalex.org/W3103667349","https://openalex.org/W3105977086","https://openalex.org/W3169283738","https://openalex.org/W3173486678","https://openalex.org/W3173825754","https://openalex.org/W3175627818","https://openalex.org/W3180230246","https://openalex.org/W3184222203","https://openalex.org/W3191403450","https://openalex.org/W3196679537","https://openalex.org/W3198480521","https://openalex.org/W3203465137","https://openalex.org/W4252076394","https://openalex.org/W4280586943","https://openalex.org/W4287887100","https://openalex.org/W6720712767","https://openalex.org/W6743367031","https://openalex.org/W6755207826","https://openalex.org/W6767970677","https://openalex.org/W6777615688","https://openalex.org/W6796679922","https://openalex.org/W6798821717"],"related_works":["https://openalex.org/W1965623300","https://openalex.org/W3134365128","https://openalex.org/W2541135911","https://openalex.org/W2359259132","https://openalex.org/W2624542985","https://openalex.org/W4387489691","https://openalex.org/W2103835134","https://openalex.org/W2740842929","https://openalex.org/W1529630694","https://openalex.org/W3190080120"],"abstract_inverted_index":{"Tables":[0],"can":[1,23],"contain":[2],"various":[3],"types":[4],"of":[5,19,48,67,88],"errors,":[6],"including":[7],"both":[8],"syntactic":[9],"and":[10,22,43,97,116],"semantic":[11,33,86],"errors.":[12],"Semantic":[13],"errors":[14],"relate":[15],"to":[16,63,83,101],"the":[17,20,46,65,85,103,119,125],"meaning":[18],"data":[21,82],"be":[24],"detrimental":[25],"for":[26,32],"downstream":[27],"applications.":[28],"The":[29],"existing":[30],"approaches":[31],"error":[34,104],"detection":[35,105],"use":[36],"structured":[37],"knowledge":[38],"sources":[39,50],"such":[40,49],"as":[41],"Wikidata":[42],"DBpedia,":[44],"but":[45],"coverage":[47],"is":[51,55],"quite":[52],"limited.":[53],"There":[54],"much":[56],"more":[57],"information":[58],"available":[59],"in":[60,111,118],"free":[61],"text":[62],"validate":[64],"contents":[66],"tables.":[68,89],"In":[69],"this":[70],"paper,":[71],"we":[72],"present":[73],"a":[74,112],"novel":[75],"semantic-error-detection":[76],"approach":[77,91,110],"that":[78,121],"exploits":[79],"open-domain":[80],"textual":[81],"verify":[84],"correctness":[87],"Our":[90],"leverages":[92],"contrastive":[93],"learning,":[94],"table":[95],"linearization,":[96],"pre-trained":[98],"language":[99],"models":[100],"implement":[102,108],"process.":[106],"We":[107],"our":[109],"system":[113],"called":[114],"SEED":[115],"show":[117],"evaluation":[120],"it":[122],"significantly":[123],"outperforms":[124],"other":[126],"competing":[127],"approaches.":[128]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}