{"id":"https://openalex.org/W4411673827","doi":"https://doi.org/10.1145/3746226","title":"Towards Automating Domain-Specific Data Generation for Text-to-SQL: A Comprehensive Approach","display_name":"Towards Automating Domain-Specific Data Generation for Text-to-SQL: A Comprehensive Approach","publication_year":2025,"publication_date":"2025-06-26","ids":{"openalex":"https://openalex.org/W4411673827","doi":"https://doi.org/10.1145/3746226"},"language":"en","primary_location":{"id":"doi:10.1145/3746226","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746226","pdf_url":null,"source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-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/A5116000547","display_name":"Salmane Chafik","orcid":null},"institutions":[{"id":"https://openalex.org/I4210131560","display_name":"Universit\u00e9 Mohammed VI Polytechnique","ror":"https://ror.org/03xc55g68","country_code":"MA","type":"education","lineage":["https://openalex.org/I4210131560"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Salmane Chafik","raw_affiliation_strings":["College of Computing, Mohammed VI Polytechnic University, Ben Guerir, Morocco","Mohammed VI Polytechnic University, Morocco"],"raw_orcid":"https://orcid.org/0009-0002-9387-6847","affiliations":[{"raw_affiliation_string":"College of Computing, Mohammed VI Polytechnic University, Ben Guerir, Morocco","institution_ids":["https://openalex.org/I4210131560"]},{"raw_affiliation_string":"Mohammed VI Polytechnic University, Morocco","institution_ids":["https://openalex.org/I4210131560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009803558","display_name":"Saad Ezzini","orcid":"https://orcid.org/0000-0001-7657-4738"},"institutions":[{"id":"https://openalex.org/I134085113","display_name":"King Fahd University of Petroleum and Minerals","ror":"https://ror.org/03yez3163","country_code":"SA","type":"education","lineage":["https://openalex.org/I134085113"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Saad Ezzini","raw_affiliation_strings":["Information and Computer Science Department, King Fahd University of Petroleum & Minerals, Dhahran, Saudi Arabia and Interdisciplinary Research Center for Intelligent Manufacturing and Robotics, King Fahd University of Petroleum & Minerals, Dhahran, Saudi Arabia","Information and Computer Science Department, KFUPM, Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0001-7657-4738","affiliations":[{"raw_affiliation_string":"Information and Computer Science Department, King Fahd University of Petroleum & Minerals, Dhahran, Saudi Arabia and Interdisciplinary Research Center for Intelligent Manufacturing and Robotics, King Fahd University of Petroleum & Minerals, Dhahran, Saudi Arabia","institution_ids":["https://openalex.org/I134085113"]},{"raw_affiliation_string":"Information and Computer Science Department, KFUPM, Saudi Arabia","institution_ids":["https://openalex.org/I134085113"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091770877","display_name":"Isma\u00efl Berrada","orcid":"https://orcid.org/0000-0003-4225-911X"},"institutions":[{"id":"https://openalex.org/I4210131560","display_name":"Universit\u00e9 Mohammed VI Polytechnique","ror":"https://ror.org/03xc55g68","country_code":"MA","type":"education","lineage":["https://openalex.org/I4210131560"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Ismail Berrada","raw_affiliation_strings":["College of Computing, Mohammed VI Polytechnic University, Ben Guerir, Morocco","Mohammed VI Polytechnic University, Morocco"],"raw_orcid":"https://orcid.org/0000-0003-4225-911X","affiliations":[{"raw_affiliation_string":"College of Computing, Mohammed VI Polytechnic University, Ben Guerir, Morocco","institution_ids":["https://openalex.org/I4210131560"]},{"raw_affiliation_string":"Mohammed VI Polytechnic University, Morocco","institution_ids":["https://openalex.org/I4210131560"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5805,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91774223,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"35","issue":"4","first_page":"1","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/T11986","display_name":"Scientific Computing and Data Management","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9957000017166138,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8910955190658569},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.6140968203544617},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4702067971229553},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4477859437465668},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.42148810625076294},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.396004319190979},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35733336210250854}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8910955190658569},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.6140968203544617},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4702067971229553},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4477859437465668},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.42148810625076294},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.396004319190979},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35733336210250854},{"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:10.1145/3746226","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746226","pdf_url":null,"source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2077302143","https://openalex.org/W2101105183","https://openalex.org/W2750779823","https://openalex.org/W2886362482","https://openalex.org/W2981852735","https://openalex.org/W3022196370","https://openalex.org/W3185858112","https://openalex.org/W3214600982","https://openalex.org/W4280534475","https://openalex.org/W4288089799","https://openalex.org/W4308245305","https://openalex.org/W4317716303","https://openalex.org/W4321153003","https://openalex.org/W4399450035","https://openalex.org/W4402977990","https://openalex.org/W6892464000"],"related_works":["https://openalex.org/W2003932708","https://openalex.org/W1967424056","https://openalex.org/W2284877871","https://openalex.org/W2138102289","https://openalex.org/W868043274","https://openalex.org/W2513523087","https://openalex.org/W1187916458","https://openalex.org/W2373861055","https://openalex.org/W1559716973","https://openalex.org/W4320802139"],"abstract_inverted_index":{"As":[0,97],"software":[1,191],"systems":[2,14,208],"increasingly":[3],"rely":[4],"on":[5,136,145],"natural":[6,26],"language":[7,27,132],"interfaces,":[8],"ensuring":[9],"the":[10,21,39,49,166,182,186],"reliability":[11,188],"of":[12,41,51,100,168,189],"these":[13,58],"is":[15,20],"crucial.":[16],"One":[17],"critical":[18],"component":[19],"ability":[22],"to":[23,70,76,87,184],"accurately":[24],"translate":[25],"queries":[28],"into":[29],"corresponding":[30],"SQL":[31],"queries,":[32],"a":[33,64,98,106,129,139],"field":[34],"known":[35],"as":[36,112],"Text-to-SQL.":[37],"However,":[38],"scarcity":[40],"high-quality,":[42],"large-scale,":[43],"and":[44,53,84,143,163,197],"domain-specific":[45,170],"Text-to-SQL":[46,73,109,173,190],"datasets":[47,74],"hinders":[48],"development":[50],"reliable":[52],"robust":[54],"models.":[55],"To":[56],"tackle":[57],"challenges,":[59],"we":[60,102,125],"propose":[61],"SelectCraft":[62],",":[63,114,128,138],"novel":[65],"automatic":[66],"generation":[67],"approach":[68],"designed":[69],"create":[71],"realistic":[72],"tailored":[75],"specific":[77],"domains.":[78],"Our":[79],"method":[80],"leverages":[81],"existing":[82],"databases":[83],"their":[85],"structures":[86],"generate":[88],"complex":[89],"text-SQL":[90],"pairs":[91],"that":[92,178],"mirror":[93],"real-world":[94],"usage":[95],"scenarios.":[96],"proof":[99],"concept,":[101],"have":[103,181],"successfully":[104],"generated":[105],"substantial":[107],"financial":[108],"dataset,":[110],"denominated":[111],"BanQies":[113],"encompassing":[115],"over":[116],"1":[117],"million":[118],"samples":[119],"utilizing":[120],"our":[121,146,179],"proposed":[122],"approach.":[123],"Moreover,":[124],"introduce":[126],"BanQL":[127,152],"new":[130],"large":[131],"model":[133],"(LLM)":[134],"based":[135],"StarCoder2":[137],"state-of-the-art":[140,156],"code-based":[141],"LLM,":[142],"fine-tuned":[144],"newly":[147],"created":[148],"dataset.":[149],"We":[150,175],"evaluate":[151],"performance":[153],"against":[154],"several":[155],"models,":[157],"demonstrating":[158],"significant":[159],"enhancements":[160],"in":[161,172],"accuracy":[162],"generalizability,":[164],"highlighting":[165],"advantages":[167],"incorporating":[169],"data":[171],"tasks.":[174],"firmly":[176],"believe":[177],"contributions":[180],"potential":[183],"improve":[185],"overall":[187],"systems.":[192],"CCS":[193],"Concepts:":[194],"\u2022":[195,200,206],"Software":[196],"its":[198],"engineering;":[199],"Computing":[201],"methodologies":[202],"\u2192":[203,209],"Natural":[204],"languageprocessing;":[205],"Information":[207],"Structured":[210],"Query":[211],"Language;":[212]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}