{"id":"https://openalex.org/W4402594071","doi":"https://doi.org/10.1109/sds60720.2024.00047","title":"Cleaning Semi-Structured Errors in Open Data Using Large Language Models","display_name":"Cleaning Semi-Structured Errors in Open Data Using Large Language Models","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4402594071","doi":"https://doi.org/10.1109/sds60720.2024.00047"},"language":"en","primary_location":{"id":"doi:10.1109/sds60720.2024.00047","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/sds60720.2024.00047","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 11th IEEE Swiss Conference on Data Science (SDS)","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/A5099447644","display_name":"Manuel Mondal","orcid":null},"institutions":[{"id":"https://openalex.org/I154338468","display_name":"University of Fribourg","ror":"https://ror.org/022fs9h90","country_code":"CH","type":"education","lineage":["https://openalex.org/I154338468"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Manuel Mondal","raw_affiliation_strings":["Université de Fribourg,Switzerland"],"affiliations":[{"raw_affiliation_string":"Université de Fribourg,Switzerland","institution_ids":["https://openalex.org/I154338468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038633752","display_name":"Julien Audiffren","orcid":"https://orcid.org/0000-0003-4321-2575"},"institutions":[{"id":"https://openalex.org/I154338468","display_name":"University of Fribourg","ror":"https://ror.org/022fs9h90","country_code":"CH","type":"education","lineage":["https://openalex.org/I154338468"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Julien Audiffren","raw_affiliation_strings":["Université de Fribourg,Switzerland"],"affiliations":[{"raw_affiliation_string":"Université de Fribourg,Switzerland","institution_ids":["https://openalex.org/I154338468"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064542836","display_name":"Ljiljana Dolamic","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ljiljana Dolamic","raw_affiliation_strings":["Armasuisse W+T,Switzerland"],"affiliations":[{"raw_affiliation_string":"Armasuisse W+T,Switzerland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099447645","display_name":"G\u00e9r\u00f4me Bovet","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"G\u00e9r\u00f4me Bovet","raw_affiliation_strings":["Armasuisse W+T,Switzerland"],"affiliations":[{"raw_affiliation_string":"Armasuisse W+T,Switzerland","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028454093","display_name":"Philippe Cudr\u00e9-Mauroux","orcid":"https://orcid.org/0000-0003-2588-4212"},"institutions":[{"id":"https://openalex.org/I154338468","display_name":"University of Fribourg","ror":"https://ror.org/022fs9h90","country_code":"CH","type":"education","lineage":["https://openalex.org/I154338468"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Philippe Cudr\u00e9-Mauroux","raw_affiliation_strings":["Université de Fribourg,Switzerland"],"affiliations":[{"raw_affiliation_string":"Université de Fribourg,Switzerland","institution_ids":["https://openalex.org/I154338468"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5099447644"],"corresponding_institution_ids":["https://openalex.org/I154338468"],"apc_list":null,"apc_paid":null,"fwci":0.6982,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.75753893,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"258","last_page":"261"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.8586000204086304,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.8586000204086304,"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/T10028","display_name":"Topic Modeling","score":0.7628999948501587,"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":0.7577242851257324},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5163925290107727},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.44834843277931213},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4130278527736664},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3346019983291626},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.20924881100654602}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7577242851257324},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5163925290107727},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.44834843277931213},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4130278527736664},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3346019983291626},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.20924881100654602}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sds60720.2024.00047","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/sds60720.2024.00047","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 11th IEEE Swiss Conference on Data Science (SDS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1971803422","https://openalex.org/W4237832002","https://openalex.org/W4253707770","https://openalex.org/W4313433600","https://openalex.org/W4321448364","https://openalex.org/W4385245566","https://openalex.org/W4389524337","https://openalex.org/W4389539730","https://openalex.org/W4399513333","https://openalex.org/W6679436768","https://openalex.org/W6778883912","https://openalex.org/W7001377637"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Many":[0],"datasets":[1],"suffer":[2],"from":[3],"errors,":[4],"rendering":[5],"data":[6,24,33,58],"cleaning,":[7],"the":[8,57,61,66,71,91],"process":[9],"of":[10,46,93,109],"rectifying":[11],"these":[12],"issues,":[13],"very":[14],"time-consuming.":[15],"The":[16],"most":[17],"commonly":[18],"studied":[19],"errors":[20,47],"encompass":[21],"inaccuracies":[22],"in":[23],"values":[25,59,67],"or":[26],"labels":[27],"(data":[28],"errors)":[29],"and":[30,60,75,100],"issues":[31],"with":[32],"formatting":[34],"that":[35],"hinder":[36],"parsing":[37,77],"(structured":[38],"errors).":[39],"We":[40],"focus":[41],"on":[42,105],"a":[43,106],"distinct":[44],"category":[45],"known":[48],"as":[49],"Semi-Structured":[50],"Errors":[51],"(SSEs),":[52],"which":[53],"occur":[54],"when":[55],"both":[56],"structure":[62],"are":[63,68],"correct,":[64],"but":[65],"misplaced":[69],"within":[70],"structure,":[72],"requiring":[73],"time-demanding":[74],"complex":[76],"rules":[78],"(including":[79],"their":[80],"exceptions)":[81],"to":[82,97],"account":[83],"for":[84],"them.":[85],"In":[86],"this":[87],"work,":[88],"we":[89],"explore":[90],"capabilities":[92],"Large":[94],"Language":[95],"Models":[96],"clean":[98],"SSEs":[99],"show":[101],"promising":[102],"experimental":[103],"results":[104],"public":[107],"dataset":[108],"Swiss":[110],"federal":[111],"law.":[112]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}