{"id":"https://openalex.org/W4401023377","doi":"https://doi.org/10.3233/ds-240062","title":"Detecting CSV file dialects by table uniformity measurement and data type\u00a0inference","display_name":"Detecting CSV file dialects by table uniformity measurement and data type\u00a0inference","publication_year":2024,"publication_date":"2024-07-26","ids":{"openalex":"https://openalex.org/W4401023377","doi":"https://doi.org/10.3233/ds-240062"},"language":"en","primary_location":{"id":"doi:10.3233/ds-240062","is_oa":true,"landing_page_url":"https://doi.org/10.3233/ds-240062","pdf_url":"https://content.iospress.com:443/download/data-science/ds240062?id=data-science%2Fds240062","source":{"id":"https://openalex.org/S4210178722","display_name":"Data Science","issn_l":"2451-8484","issn":["2451-8484","2451-8492"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://content.iospress.com:443/download/data-science/ds240062?id=data-science%2Fds240062","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019315873","display_name":"Wilfredo Garc\u00eda","orcid":"https://orcid.org/0000-0002-9620-1119"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wilfredo Garc\u00eda","raw_affiliation_strings":["CEO office, ECP Solutions, Santiago, Rep\u00fablica Dominicana"],"raw_orcid":"https://orcid.org/0000-0002-9620-1119","affiliations":[{"raw_affiliation_string":"CEO office, ECP Solutions, Santiago, Rep\u00fablica Dominicana","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5019315873"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2778,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.60360675,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"7","issue":"2","first_page":"55","last_page":"72"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9965000152587891,"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":0.9965000152587891,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9886999726295471,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9667999744415283,"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":0.7277296781539917},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.6289595365524292},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5820085406303406},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.505558967590332},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.5011308193206787},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.47242748737335205},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4372977614402771},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3056200444698334},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2946147918701172},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.21022272109985352}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7277296781539917},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.6289595365524292},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5820085406303406},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.505558967590332},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5011308193206787},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47242748737335205},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4372977614402771},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3056200444698334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2946147918701172},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.21022272109985352}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3233/ds-240062","is_oa":true,"landing_page_url":"https://doi.org/10.3233/ds-240062","pdf_url":"https://content.iospress.com:443/download/data-science/ds240062?id=data-science%2Fds240062","source":{"id":"https://openalex.org/S4210178722","display_name":"Data Science","issn_l":"2451-8484","issn":["2451-8484","2451-8492"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Science","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-04663419v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04663419","pdf_url":"https://hal.science/hal-04663419/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data Science, In press, 7 (2), pp.1-18. ⟨10.3233/DS-240062⟩","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:8495b0a18b994f9aa01fec20c122c42a","is_oa":true,"landing_page_url":"https://doaj.org/article/8495b0a18b994f9aa01fec20c122c42a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data Science, Vol 7 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3233/ds-240062","is_oa":true,"landing_page_url":"https://doi.org/10.3233/ds-240062","pdf_url":"https://content.iospress.com:443/download/data-science/ds240062?id=data-science%2Fds240062","source":{"id":"https://openalex.org/S4210178722","display_name":"Data Science","issn_l":"2451-8484","issn":["2451-8484","2451-8492"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401023377.pdf","grobid_xml":"https://content.openalex.org/works/W4401023377.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W2155970976","https://openalex.org/W2179242664","https://openalex.org/W2522705507","https://openalex.org/W2555658823","https://openalex.org/W2623925395","https://openalex.org/W2809161078","https://openalex.org/W2902696364","https://openalex.org/W3082162291","https://openalex.org/W3099161928","https://openalex.org/W4381621958","https://openalex.org/W6906714556"],"related_works":["https://openalex.org/W4394360958","https://openalex.org/W579810227","https://openalex.org/W2952780262","https://openalex.org/W2979495269","https://openalex.org/W2392917763","https://openalex.org/W4221163897","https://openalex.org/W6643695","https://openalex.org/W4381248170","https://openalex.org/W3189621521","https://openalex.org/W2173794830"],"abstract_inverted_index":{"The":[0,38,157],"human-readable":[1],"simplicity":[2],"with":[3,11,32,148,168,242,289],"which":[4,33,243],"the":[5,12,24,30,43,60,70,81,101,149,182,187,190,212,217,221,240,256,278,284],"CSV":[6,84,130,170,188,206],"format":[7],"was":[8],"devised,":[9],"together":[10],"absence":[13],"of":[14,26,45,72,83,151,173,211,229,236],"a":[15,97,105,126,136,161,166,177,290],"standard":[16],"that":[17,42,76,116],"strictly":[18],"defines":[19],"this":[20,252],"format,":[21],"has":[22,40,67,160],"allowed":[23],"proliferation":[25],"several":[27],"variants":[28],"in":[29,86,96,232,239],"dialects":[31,82,132,244,264],"these":[34],"files":[35,171,207],"are":[36,245],"written.":[37],"latter":[39],"meant":[41],"exchange":[44],"information":[46,286],"between":[47,52],"data":[48,61,90,93,152,178,197,250,272],"management":[49],"systems,":[50],"or":[51,113],"countries":[53],"and":[54,63,108,143,203],"regions,":[55],"requires":[56],"human":[57],"intervention":[58],"during":[59],"mining":[62],"cleansing":[64],"process.":[65],"This":[66,123],"led":[68],"to":[69,78,88,118,262,273,287],"development":[71,202],"various":[73],"computational":[74],"tools":[75],"aim":[77],"accurately":[79],"determine":[80,263],"files,":[85],"order":[87],"avoid":[89],"loss":[91],"at":[92],"loading":[94],"stage":[95],"given":[98],"system.":[99],"However,":[100],"dialect":[102,291],"detection":[103,150],"is":[104,259],"complex":[106],"problem":[107],"current":[109],"systems":[110],"have":[111],"limitations":[112],"make":[114],"assumptions":[115],"need":[117],"be":[119],"improved":[120],"and/or":[121],"extended.":[122],"paper":[124],"proposes":[125],"method":[127,159,258],"for":[128,251],"determining":[129],"file":[131],"through":[133],"table":[134,141],"uniformity,":[135],"statistical":[137],"approach":[138],"based":[139],"on":[140,165,189,247],"consistency":[142],"records":[144,280],"dispersion":[145],"measurement":[146],"along":[147],"type":[153],"over":[154],"each":[155],"field.":[156],"new":[158],"93.38%":[162],"average":[163,227],"accuracy":[164,241],"dataset":[167],"548":[169],"composed":[172],"samples":[174],"coming":[175],"from":[176,199],"load":[179],"testing":[180],"framework,":[181],"test":[183],"suite":[184],"provided":[185],"by":[186,224,265],"Web":[191],"Working":[192],"Group":[193],"(CSVW),":[194],"curated":[195],"experimental":[196],"set":[198],"similar":[200],"tool":[201,223],"some":[204],"others":[205],"added":[208],"as":[209],"verification":[210],"parsing":[213],"routines.":[214],"In":[215],"tests,":[216],"proposed":[218,257],"solution":[219],"outperforms":[220],"state-of-the-art":[222],"achieving":[225],"an":[226,233],"improvement":[228],"16.45%,":[230],"resulting":[231],"net":[234],"increment":[235],"about":[237],"10%":[238],"detected":[246],"truly":[248],"messy":[249],"research":[253],"dataset.":[254],"Furthermore,":[255],"accurate":[260],"enough":[261],"reading":[266],"only":[267],"ten":[268],"records,":[269],"requiring":[270],"more":[271],"disambiguate":[274],"those":[275],"cases":[276],"where":[277],"first":[279],"do":[281],"not":[282],"contain":[283],"necessary":[285],"conclude":[288],"determination.":[292]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}