{"id":"https://openalex.org/W4286980193","doi":"https://doi.org/10.48550/arxiv.2109.05157","title":"Exploring Underexplored Limitations of Cross-Domain Text-to-SQL Generalization","display_name":"Exploring Underexplored Limitations of Cross-Domain Text-to-SQL Generalization","publication_year":2021,"publication_date":"2021-09-11","ids":{"openalex":"https://openalex.org/W4286980193","doi":"https://doi.org/10.48550/arxiv.2109.05157"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2109.05157","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.05157","pdf_url":"https://arxiv.org/pdf/2109.05157","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2109.05157","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069122194","display_name":"Yujian Gan","orcid":"https://orcid.org/0009-0002-3188-5924","observed_orcids":["https://orcid.org/0009-0002-3188-5924"]},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gan, Yujian","raw_affiliation_strings":["Queen Mary University of London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London","institution_ids":["https://openalex.org/I166337079"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chen, Xinyun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen, Xinyun","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047970122","display_name":"Matthew Purver","orcid":"https://orcid.org/0000-0003-2297-1273","observed_orcids":["https://orcid.org/0000-0003-2297-1273"]},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]},{"id":"https://openalex.org/I3006985408","display_name":"Jo\u017eef Stefan Institute","ror":"https://ror.org/05060sz93","country_code":"SI","type":"facility","lineage":["https://openalex.org/I3006985408"]},{"id":"https://openalex.org/I4210113529","display_name":"Jo\u017eef Stefan International Postgraduate School","ror":"https://ror.org/01hdkb925","country_code":"SI","type":"education","lineage":["https://openalex.org/I4210113529"]}],"countries":["GB","SI"],"is_corresponding":false,"raw_author_name":"Purver, Matthew","raw_affiliation_strings":["Jo\u017eef Stefan Institute","Queen Mary University of London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jo\u017eef Stefan Institute","institution_ids":["https://openalex.org/I3006985408","https://openalex.org/I4210113529"]},{"raw_affiliation_string":"Queen Mary University of London","institution_ids":["https://openalex.org/I166337079"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":41,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6176999807357788,"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":0.6176999807357788,"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":0.20499999821186066,"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":0.03709999844431877,"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/text-to-sql","display_name":"text-to-SQL","score":0.984000027179718},{"id":"https://openalex.org/keywords/domain-generalization","display_name":"domain generalization","score":0.9150000214576721},{"id":"https://openalex.org/keywords/zero-shot-learning","display_name":"zero-shot learning","score":0.7250000238418579},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"domain knowledge","score":0.9259999990463257},{"id":"https://openalex.org/keywords/model-robustness","display_name":"model robustness","score":0.7260000109672546},{"id":"https://openalex.org/keywords/spider-benchmark","display_name":"Spider benchmark","score":0.7770000100135803},{"id":"https://openalex.org/keywords/limited-training-data","display_name":"limited training data","score":0.39500001072883606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8128846883773804},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.6230367422103882},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.5795723795890808},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5413185954093933},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5080430507659912},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4853021502494812},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4694019854068756},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4504585266113281},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43996235728263855},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.43862199783325195},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.41041725873947144},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.205329030752182},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15831217169761658},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06898975372314453},{"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"pmh:oai:arXiv.org:2109.05157","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.05157","pdf_url":"https://arxiv.org/pdf/2109.05157","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/74323","doi":null,"is_oa":true,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/74323","pdf_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/74323","source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/82969","doi":null,"is_oa":false,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/82969","pdf_url":null,"source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceeding"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/88782","doi":null,"is_oa":true,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/88782","pdf_url":null,"source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"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":"","raw_type":null},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/93933","doi":null,"is_oa":false,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/93933","pdf_url":null,"source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"doi:10.48550/arxiv.2109.05157","doi":"https://doi.org/10.48550/arxiv.2109.05157","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2109.05157","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2109.05157","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.05157","pdf_url":"https://arxiv.org/pdf/2109.05157","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3815504723","display_name":"Streamlining Social Decision Making for Improved Internet Standards","funder_award_id":"EP/S033564/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G434337789","display_name":null,"funder_award_id":"HORIZON2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5108423257","display_name":"Cross-Lingual Embeddings for Less-Represented Languages in European News Media","funder_award_id":"825153","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4286980193.pdf","grobid_xml":"https://content.openalex.org/works/W4286980193.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W2163274265","https://openalex.org/W2250539671","https://openalex.org/W2250770256","https://openalex.org/W2611818442","https://openalex.org/W2751448157","https://openalex.org/W2945102109","https://openalex.org/W2952032096","https://openalex.org/W2963341956","https://openalex.org/W2985377636","https://openalex.org/W3035172316","https://openalex.org/W3092967498","https://openalex.org/W3093630174","https://openalex.org/W3093819145","https://openalex.org/W3116083993","https://openalex.org/W3119897089","https://openalex.org/W3122604893","https://openalex.org/W3134835171","https://openalex.org/W3170656151"],"related_works":["https://openalex.org/W4415271606","https://openalex.org/W2984689063","https://openalex.org/W4390097854","https://openalex.org/W6893706705","https://openalex.org/W2997970380","https://openalex.org/W4389649881","https://openalex.org/W4389523781","https://openalex.org/W4317940064","https://openalex.org/W7162317768","https://openalex.org/W3152888762"],"abstract_inverted_index":{"Recently,":[0],"there":[1],"has":[2],"been":[3],"significant":[4],"progress":[5],"in":[6,48,112,153],"studying":[7],"neural":[8],"networks":[9],"for":[10,59,107,164],"translating":[11],"text":[12],"descriptions":[13],"into":[14],"SQL":[15],"queries":[16],"under":[17],"the":[18,49,55,67,73,94,104,135,149,154,158,161],"zero-shot":[19],"cross-domain":[20],"setting.":[21],"Despite":[22],"achieving":[23],"good":[24],"performance":[25,58],"on":[26,103,140],"some":[27,121],"public":[28],"benchmarks,":[29],"we":[30,65,82,119],"observe":[31],"that":[32,43,127,134,142],"existing":[33],"text-to-SQL":[34,70,108],"models":[35,71],"do":[36],"not":[37,45],"generalize":[38],"when":[39,72],"facing":[40],"domain":[41,78,87,97,125,145,150],"knowledge":[42,88,126,151],"does":[44],"frequently":[46],"appear":[47],"training":[50,155,166],"data,":[51],"which":[52],"may":[53],"render":[54],"worse":[56],"prediction":[57,136],"unseen":[60],"domains.":[61],"In":[62,80],"this":[63],"work,":[64],"investigate":[66],"robustness":[68],"of":[69,86,96],"questions":[74,111],"require":[75,143],"rarely":[76],"observed":[77],"knowledge.":[79],"particular,":[81],"define":[83],"five":[84],"types":[85],"and":[89,118,157],"introduce":[90],"Spider-DK":[91,113],"(DK":[92],"is":[93],"abbreviation":[95],"knowledge),":[98],"a":[99],"human-curated":[100],"dataset":[101],"based":[102],"Spider":[105],"benchmark":[106],"translation.":[109],"NL":[110],"are":[114],"selected":[115],"from":[116],"Spider,":[117],"modify":[120],"samples":[122,141],"by":[123],"adding":[124],"reflects":[128],"real-world":[129],"question":[130],"paraphrases.":[131],"We":[132],"demonstrate":[133],"accuracy":[137],"dramatically":[138],"drops":[139],"such":[144],"knowledge,":[146],"even":[147],"if":[148],"appears":[152],"set,":[156],"model":[159],"provides":[160],"correct":[162],"predictions":[163],"related":[165],"samples.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":6}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2025-10-10T00:00:00"}