{"id":"https://openalex.org/W4387338171","doi":"https://doi.org/10.1145/3617023.3617035","title":"DBVinci \u2013 towards the usage of GPT engine for processing SQL Queries","display_name":"DBVinci \u2013 towards the usage of GPT engine for processing SQL Queries","publication_year":2023,"publication_date":"2023-10-04","ids":{"openalex":"https://openalex.org/W4387338171","doi":"https://doi.org/10.1145/3617023.3617035"},"language":"en","primary_location":{"id":"doi:10.1145/3617023.3617035","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3617023.3617035","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3617023.3617035","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th Brazilian Symposium on Multimedia and the Web","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3617023.3617035","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103254448","display_name":"Vanessa C\u00e2mara","orcid":"https://orcid.org/0009-0001-8246-6896"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vanessa C\u00e2mara","raw_affiliation_strings":["Retail Management System, Sidia R&D Institute, Brazil"],"raw_orcid":"https://orcid.org/0009-0001-8246-6896","affiliations":[{"raw_affiliation_string":"Retail Management System, Sidia R&D Institute, Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013317137","display_name":"Rayol Mendonca-Neto","orcid":"https://orcid.org/0000-0001-9693-6417"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rayol Mendonca-Neto","raw_affiliation_strings":["Retail Management System, Sidia R&D Institute, Brazil"],"raw_orcid":"https://orcid.org/0000-0001-9693-6417","affiliations":[{"raw_affiliation_string":"Retail Management System, Sidia R&D Institute, Brazil","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064094377","display_name":"Andr\u00e9 R.F. Silva","orcid":"https://orcid.org/0000-0001-5586-7005"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andr\u00e9 Silva","raw_affiliation_strings":["Retail Management System, Sidia R&D Institute, Brazil"],"raw_orcid":"https://orcid.org/0000-0001-5586-7005","affiliations":[{"raw_affiliation_string":"Retail Management System, Sidia R&D Institute, Brazil","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113015813","display_name":"Luiz Cordovil-Jr","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luiz Cordovil-Jr","raw_affiliation_strings":["Retail Management System, Sidia R&D Institute, Brazil"],"raw_orcid":"https://orcid.org/0000-0001-9503-856X","affiliations":[{"raw_affiliation_string":"Retail Management System, Sidia R&D Institute, Brazil","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6674,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.86899904,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"91","last_page":"95"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.998199999332428,"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/T10028","display_name":"Topic Modeling","score":0.998199999332428,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9940999746322632,"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":0.9542999863624573,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8986959457397461},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.8389583826065063},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5638740658760071},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5547882318496704},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.49736288189888},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.4797957241535187},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.46395036578178406},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43437179923057556},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4287327229976654},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.42113491892814636},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3763285279273987}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8986959457397461},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.8389583826065063},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5638740658760071},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5547882318496704},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.49736288189888},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.4797957241535187},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.46395036578178406},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43437179923057556},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4287327229976654},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.42113491892814636},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3763285279273987},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3617023.3617035","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3617023.3617035","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3617023.3617035","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th Brazilian Symposium on Multimedia and the Web","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3617023.3617035","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3617023.3617035","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3617023.3617035","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th Brazilian Symposium on Multimedia and the Web","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.800000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387338171.pdf","grobid_xml":"https://content.openalex.org/works/W4387338171.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W2890431379","https://openalex.org/W2950067395","https://openalex.org/W3034835156","https://openalex.org/W3086973390","https://openalex.org/W3133070967","https://openalex.org/W4312537169"],"related_works":["https://openalex.org/W579810227","https://openalex.org/W2952780262","https://openalex.org/W2979495269","https://openalex.org/W2392917763","https://openalex.org/W1971994716","https://openalex.org/W2911292476","https://openalex.org/W2049117375","https://openalex.org/W2159231020","https://openalex.org/W1837359179","https://openalex.org/W2165504147"],"abstract_inverted_index":{"One":[0],"of":[1,4,38,81,134,144,163,177,212],"the":[2,72,79,175,184,203,213,222],"goals":[3],"Natural":[5],"Language":[6,205],"Processing":[7],"(NLP)":[8],"is":[9,65,100,106,131,209],"transforming":[10],"sentences":[11],"to":[12,44,53,59,70,74,198],"output":[13],"relevant":[14,22],"information":[15,76],"in":[16,67,149,191,221],"a":[17,82,87,142],"given":[18],"context.":[19],"For":[20],"instance,":[21],"applications":[23],"such":[24,48,118],"as":[25,49,119],"chatbots,":[26],"translation":[27],"systems,":[28],"and":[29,77,123,136,159],"sentiment":[30],"analysis":[31],"classifiers":[32],"work":[33],"that":[34,113,197],"way.":[35],"The":[36],"advance":[37],"NLP":[39],"techniques":[40],"made":[41],"it":[42,64],"possible":[43],"automate":[45],"complex":[46,138],"tasks,":[47],"converting":[50],"text":[51],"queries":[52,140],"tabular":[54],"data":[55,73],"queries,":[56],"specifically":[57],"SQL,":[58],"return":[60],"contextualized":[61],"data.":[62],"Since":[63],"crucial":[66],"many":[68],"areas":[69],"interpret":[71],"obtain":[75,171,199],"consider":[78],"particularities":[80],"text-to-SQL":[83,155],"parser,":[84],"we":[85,195,225],"propose":[86],"SQL":[88,139],"processing":[89,103,146],"engine":[90,112],"whose":[91],"internals":[92],"are":[93],"customized":[94],"with":[95],"natural":[96,150],"language":[97,116],"instructions.":[98],"DBVinci":[99,152],"our":[101],"proposed":[102,223],"model":[104],"which":[105],"based":[107],"on":[108,132],"OpenAI\u2019s":[109],"GPT-3.5":[110,135],"Text-davinci-003":[111],"can":[114,226],"perform":[115],"tasks":[117],"text-to-SQL,":[120],"consistent":[121],"instruction-following,":[122],"supports":[124],"inserting":[125],"completions":[126],"within":[127],"text.":[128],"Our":[129],"framework":[130],"top":[133],"decomposes":[137],"into":[141],"series":[143],"simple":[145],"steps,":[147],"described":[148],"language.":[151],"outperforms":[153],"well-known":[154],"methods":[156],"(e.g.,":[157],"RAT-SQL":[158],"SQLOVA)":[160],"reaching":[161],"89.7%":[162],"execution":[164],"accuracy,":[165],"considering":[166],"WikiSQL":[167],"benchmark.":[168],"We":[169],"also":[170],"impressive":[172],"performance":[173],"without":[174],"need":[176,211],"large":[178],"scale":[179],"annotated":[180],"dataset":[181],"for":[182],"fine-tuning":[183],"downstream":[185],"task,":[186],"by":[187],"achieving":[188],"90%":[189],"accuracy":[190],"zero-shot":[192,220],"setting.":[193],"Therefore,":[194],"conclude":[196],"competitive":[200],"results":[201],"using":[202],"Pre-trained":[204],"Model":[206],"(PLM),":[207],"there":[208],"no":[210],"\u201cpre-training+fine-tuning\u201d":[214],"paradigm,":[215],"besides":[216],"that,":[217],"when":[218],"employing":[219],"method,":[224],"achieve":[227],"promising":[228],"results.":[229]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3}],"updated_date":"2026-08-24T07:32:12.397491","created_date":"2025-10-10T00:00:00"}