{"id":"https://openalex.org/W3134503905","doi":"https://doi.org/10.18653/v1/2021.emnlp-main.707","title":"Data Augmentation with Hierarchical SQL-to-Question Generation for Cross-domain Text-to-SQL Parsing","display_name":"Data Augmentation with Hierarchical SQL-to-Question Generation for Cross-domain Text-to-SQL Parsing","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3134503905","doi":"https://doi.org/10.18653/v1/2021.emnlp-main.707","mag":"3134503905"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2021.emnlp-main.707","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.emnlp-main.707","pdf_url":"https://aclanthology.org/2021.emnlp-main.707.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","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":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2021.emnlp-main.707.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101898735","display_name":"Kun Wu","orcid":"https://orcid.org/0009-0009-9954-0886"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Wu","raw_affiliation_strings":[". Institute of Artificial Intelligence, School of Computer Science and Technology, Soochow University, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":". Institute of Artificial Intelligence, School of Computer Science and Technology, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100651061","display_name":"Lijie Wang","orcid":"https://orcid.org/0000-0003-1702-0422"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lijie Wang","raw_affiliation_strings":[". Baidu Inc, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":". Baidu Inc, Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100647402","display_name":"Zhenghua Li","orcid":"https://orcid.org/0000-0002-3911-801X"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenghua Li","raw_affiliation_strings":[". Institute of Artificial Intelligence, School of Computer Science and Technology, Soochow University, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":". Institute of Artificial Intelligence, School of Computer Science and Technology, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027915615","display_name":"Ao Zhang","orcid":"https://orcid.org/0000-0002-3629-5619"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ao Zhang","raw_affiliation_strings":[". Baidu Inc, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":". Baidu Inc, Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112673776","display_name":"Xinyan Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyan Xiao","raw_affiliation_strings":[". Baidu Inc, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":". Baidu Inc, Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100677198","display_name":"Hua Wu","orcid":"https://orcid.org/0000-0002-5687-7800"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hua Wu","raw_affiliation_strings":[". Baidu Inc, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":". Baidu Inc, Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100402911","display_name":"Min Zhang","orcid":"https://orcid.org/0000-0002-3895-5510"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Zhang","raw_affiliation_strings":[". Institute of Artificial Intelligence, School of Computer Science and Technology, Soochow University, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":". Institute of Artificial Intelligence, School of Computer Science and Technology, Soochow University, Suzhou, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100386394","display_name":"Haifeng Wang","orcid":"https://orcid.org/0000-0002-0672-7468"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haifeng Wang","raw_affiliation_strings":[". Baidu Inc, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":". Baidu Inc, Beijing, China","institution_ids":["https://openalex.org/I98301712"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0293,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.89168207,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"8974","last_page":"8983"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9725000262260437,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8906971216201782},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.7451536059379578},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6659746766090393},{"id":"https://openalex.org/keywords/data-definition-language","display_name":"Data definition language","score":0.5992881655693054},{"id":"https://openalex.org/keywords/stored-procedure","display_name":"Stored procedure","score":0.5366233587265015},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.46143102645874023},{"id":"https://openalex.org/keywords/query-by-example","display_name":"Query by Example","score":0.44640421867370605},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44007256627082825},{"id":"https://openalex.org/keywords/sql-injection","display_name":"SQL injection","score":0.4342302680015564},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4290786683559418},{"id":"https://openalex.org/keywords/language-integrated-query","display_name":"Language Integrated Query","score":0.4195573925971985},{"id":"https://openalex.org/keywords/abstract-syntax-tree","display_name":"Abstract syntax tree","score":0.4150266647338867},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4125830829143524},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3859666585922241},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3545517921447754},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.25725871324539185}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8906971216201782},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.7451536059379578},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6659746766090393},{"id":"https://openalex.org/C55596503","wikidata":"https://www.wikidata.org/wiki/Q1431648","display_name":"Data definition language","level":3,"score":0.5992881655693054},{"id":"https://openalex.org/C154420247","wikidata":"https://www.wikidata.org/wiki/Q846619","display_name":"Stored procedure","level":5,"score":0.5366233587265015},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.46143102645874023},{"id":"https://openalex.org/C194222762","wikidata":"https://www.wikidata.org/wiki/Q114486","display_name":"Query by Example","level":4,"score":0.44640421867370605},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44007256627082825},{"id":"https://openalex.org/C150451098","wikidata":"https://www.wikidata.org/wiki/Q506059","display_name":"SQL injection","level":5,"score":0.4342302680015564},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4290786683559418},{"id":"https://openalex.org/C179531526","wikidata":"https://www.wikidata.org/wiki/Q595637","display_name":"Language Integrated Query","level":5,"score":0.4195573925971985},{"id":"https://openalex.org/C58646249","wikidata":"https://www.wikidata.org/wiki/Q127380","display_name":"Abstract syntax tree","level":3,"score":0.4150266647338867},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4125830829143524},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3859666585922241},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3545517921447754},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25725871324539185},{"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},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2021.emnlp-main.707","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.emnlp-main.707","pdf_url":"https://aclanthology.org/2021.emnlp-main.707.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","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":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2021.emnlp-main.707","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2021.emnlp-main.707","pdf_url":"https://aclanthology.org/2021.emnlp-main.707.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","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":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6399999856948853}],"awards":[{"id":"https://openalex.org/G1663958928","display_name":null,"funder_award_id":"62176173","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327518","display_name":"Priority Academic Program Development of Jiangsu Higher Education Institutions","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3134503905.pdf","grobid_xml":"https://content.openalex.org/works/W3134503905.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1580423347","https://openalex.org/W2097117768","https://openalex.org/W2107130271","https://openalex.org/W2251658415","https://openalex.org/W2269738476","https://openalex.org/W2751448157","https://openalex.org/W2762513422","https://openalex.org/W2886983157","https://openalex.org/W2890431379","https://openalex.org/W2890867094","https://openalex.org/W2891691255","https://openalex.org/W2892131163","https://openalex.org/W2896457183","https://openalex.org/W2912624765","https://openalex.org/W2945102109","https://openalex.org/W2962721878","https://openalex.org/W2963207291","https://openalex.org/W2963341956","https://openalex.org/W2963655793","https://openalex.org/W2964120993","https://openalex.org/W2964165364","https://openalex.org/W2964271186","https://openalex.org/W2970544186","https://openalex.org/W2971296908","https://openalex.org/W3013119194","https://openalex.org/W3035140194","https://openalex.org/W3035231859","https://openalex.org/W3091229675","https://openalex.org/W3098341425","https://openalex.org/W3116083993","https://openalex.org/W4287550997","https://openalex.org/W4287659415","https://openalex.org/W4288025992","https://openalex.org/W4288601872","https://openalex.org/W4289406345","https://openalex.org/W4289494028"],"related_works":["https://openalex.org/W151073879","https://openalex.org/W619366292","https://openalex.org/W2803214644","https://openalex.org/W4386768611","https://openalex.org/W4238156210","https://openalex.org/W2359391484","https://openalex.org/W2340883001","https://openalex.org/W638381921","https://openalex.org/W2750425440","https://openalex.org/W2884764431"],"abstract_inverted_index":{"Data":[0],"augmentation":[1,67,172],"has":[2],"attracted":[3],"a":[4,62,71,76,114,136],"lot":[5],"of":[6,23,49,79,99,130,149],"research":[7],"attention":[8],"in":[9,17,102,161,165],"the":[10,32,47,103,127,182,187,190],"deep":[11],"learning":[12],"era":[13],"for":[14,26,35,189],"its":[15],"ability":[16],"alleviating":[18],"data":[19,25,66,105,171],"sparseness.":[20],"The":[21],"lack":[22],"labeled":[24],"unseen":[27],"evaluation":[28],"databases":[29],"is":[30,126,186],"exactly":[31],"major":[33,128],"challenge":[34],"cross-domain":[36,155],"text-to-SQL":[37],"parsing.":[38],"Previous":[39],"works":[40],"either":[41],"require":[42,94],"human":[43],"intervention":[44],"to":[45,54,119],"guarantee":[46],"quality":[48],"generated":[50,109,150],"data,":[51],"or":[52],"fail":[53],"handle":[55],"complex":[56],"SQL":[57,80,100],"queries.":[58,110],"This":[59],"paper":[60],"presents":[61],"simple":[63,137],"yet":[64],"effective":[65],"framework.":[68],"First,":[69],"given":[70,146],"database,":[72],"we":[73,93,112,134],"automatically":[74],"produce":[75],"large":[77,147],"number":[78],"queries":[81],"based":[82],"on":[83,153],"an":[84],"abstract":[85],"syntax":[86],"tree":[87],"grammar.":[88],"For":[89],"better":[90],"distribution":[91],"matching,":[92],"that":[95,140,168],"at":[96],"least":[97],"80%":[98],"patterns":[101],"training":[104,144],"are":[106],"covered":[107],"by":[108],"Second,":[111],"propose":[113],"hierarchical":[115,183],"SQL-to-question":[116],"generation":[117,184],"model":[118],"obtain":[120],"high-quality":[121],"natural":[122],"language":[123],"questions,":[124],"which":[125],"contribution":[129],"this":[131],"work.":[132],"Finally,":[133],"design":[135],"sampling":[138],"strategy":[139],"can":[141,174],"greatly":[142],"improve":[143,176],"efficiency":[145],"amounts":[148],"data.":[151],"Experiments":[152],"three":[154],"datasets,":[156],"i.e.,":[157],"WikiSQL":[158],"and":[159,163,181],"Spider":[160],"English,":[162],"DuSQL":[164],"Chinese,":[166],"show":[167],"our":[169],"proposed":[170],"framework":[173],"consistently":[175],"performance":[177],"over":[178],"strong":[179],"baselines,":[180],"component":[185],"key":[188],"improvement.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}