{"id":"https://openalex.org/W4416035946","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.190","title":"Learning SQL Like a Human: Structure-Aware Curriculum Learning for Text-to-SQL Generation","display_name":"Learning SQL Like a Human: Structure-Aware Curriculum Learning for Text-to-SQL Generation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035946","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.190"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.190","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.190","pdf_url":"https://aclanthology.org/2025.findings-emnlp.190.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.190.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111363044","display_name":"Xiaohu Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaohu Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073922452","display_name":"Qian Li","orcid":"https://orcid.org/0000-0002-0110-451X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002613045","display_name":"Lizhen Cui","orcid":"https://orcid.org/0000-0003-4977-7577"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lizhen Cui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101920358","display_name":"Yuntao Du","orcid":"https://orcid.org/0000-0003-0620-5704"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuntao Du","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3545","last_page":"3559"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.18880000710487366,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.18880000710487366,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T13034","display_name":"Information Systems Education and Curriculum Development","score":0.17649999260902405,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.039900001138448715,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/curriculum","display_name":"Curriculum","score":0.4481000006198883},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.40869998931884766},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.27459999918937683},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.2660999894142151},{"id":"https://openalex.org/keywords/experiential-learning","display_name":"Experiential learning","score":0.2646999955177307}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6532999873161316},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.4481000006198883},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.40869998931884766},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.38359999656677246},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31459999084472656},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C37228920","wikidata":"https://www.wikidata.org/wiki/Q1307600","display_name":"Experiential learning","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2538999915122986},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.190","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.190","pdf_url":"https://aclanthology.org/2025.findings-emnlp.190.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.190","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.190","pdf_url":"https://aclanthology.org/2025.findings-emnlp.190.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311026","display_name":"Shandong University","ror":"https://ror.org/0207yh398"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null},{"id":"https://openalex.org/F4320324852","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035946.pdf","grobid_xml":"https://content.openalex.org/works/W4416035946.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"Text-to-SQL":[1],"capabilities":[2],"of":[3],"large":[4],"language":[5],"allow":[6],"users":[7],"to":[8,20,37,90,106],"interact":[9],"with":[10,22,43,60,78],"databases":[11],"using":[12],"natural":[13],"language.Despite":[14],"recent":[15],"advances,":[16],"existing":[17],"models":[18,70,136],"continue":[19],"struggle":[21],"complex":[23,108],"queries,":[24],"particularly":[25],"those":[26],"requiring":[27],"multitable":[28],"joins":[29],"and":[30,114,126,134,139],"reasoning.To":[31],"address":[32],"this":[33],"gap,":[34],"we":[35,67,82],"propose":[36],"construct":[38],"a":[39,49,61,72,84],"model,":[40],"namely":[41],"SAC-SQL,":[42],"synthetic":[44],"training":[45,93],"samples":[46,94],"followed":[47],"by":[48],"structure-aware":[50],"curriculum":[51,97],"learning":[52,103],"framework":[53],"for":[54],"enhancing":[55],"SQL":[56,76,109],"generation.Our":[57],"approach":[58],"begins":[59],"supervised":[62],"finetuning":[63],"(SFT)":[64],"stage,":[65],"where":[66],"train":[68],"open-source":[69,133],"on":[71,137],"synthetically":[73],"constructed,":[74],"crossdomain":[75],"dataset":[77],"diverse":[79],"structural":[80],"patterns.Moreover,":[81],"introduce":[83],"unified":[85],"structure":[86],"difficulty":[87],"scoring":[88],"function":[89],"partition":[91],"the":[92,100,115,124,129],"into":[95],"non-overlapping":[96],"phases,":[98],"guiding":[99],"model":[101],"progressively":[102],"from":[104],"simpler":[105],"more":[107],"structures.Extensive":[110],"experiments":[111],"are":[112],"conducted":[113],"results":[116,122],"show":[117],"that":[118],"SAC-SQL":[119],"achieves":[120],"better":[121],"than":[123],"baselines,":[125],"significantly":[127],"narrows":[128],"performance":[130],"gap":[131],"between":[132],"close-source":[135],"Spider":[138],"Bird":[140],"benchmarks.":[141]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}