{"id":"https://openalex.org/W4411630271","doi":"https://doi.org/10.18653/v1/2024.eacl-long.6","title":"Archer: A Human-Labeled Text-to-SQL Dataset with Arithmetic, Commonsense and Hypothetical Reasoning","display_name":"Archer: A Human-Labeled Text-to-SQL Dataset with Arithmetic, Commonsense and Hypothetical Reasoning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4411630271","doi":"https://doi.org/10.18653/v1/2024.eacl-long.6"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.eacl-long.6","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.eacl-long.6","pdf_url":"https://aclanthology.org/2024.eacl-long.6.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":"Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.eacl-long.6.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062319780","display_name":"Danna Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Danna Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041024491","display_name":"Mirella Lapata","orcid":"https://orcid.org/0000-0002-2107-1516"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mirella Lapata","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5066422711","display_name":"Jeff Z. Pan","orcid":"https://orcid.org/0000-0002-9779-2088"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeff Pan","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":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"94","last_page":"111"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9782000184059143,"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":0.9782000184059143,"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":0.9433000087738037,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9003999829292297,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7315104007720947},{"id":"https://openalex.org/keywords/commonsense-reasoning","display_name":"Commonsense reasoning","score":0.6438884139060974},{"id":"https://openalex.org/keywords/commonsense-knowledge","display_name":"Commonsense knowledge","score":0.5686516165733337},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47543954849243164},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.45002609491348267},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.4094742238521576},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40479210019111633},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3671709895133972},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17732226848602295},{"id":"https://openalex.org/keywords/knowledge-based-systems","display_name":"Knowledge-based systems","score":0.10565224289894104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7315104007720947},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.6438884139060974},{"id":"https://openalex.org/C30542707","wikidata":"https://www.wikidata.org/wiki/Q1603203","display_name":"Commonsense knowledge","level":3,"score":0.5686516165733337},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47543954849243164},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.45002609491348267},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.4094742238521576},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40479210019111633},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3671709895133972},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17732226848602295},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.10565224289894104}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2024.eacl-long.6","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.eacl-long.6","pdf_url":"https://aclanthology.org/2024.eacl-long.6.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":"Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/8c5b5d00-53ee-44dd-a3f2-598c08556740","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/8c5b5d00-53ee-44dd-a3f2-598c08556740","pdf_url":null,"source":{"id":"https://openalex.org/S4306400321","display_name":"Edinburgh Research Explorer (University of Edinburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98677209","host_organization_name":"University of Edinburgh","host_organization_lineage":["https://openalex.org/I98677209"],"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":"Zheng, D, Lapata, M & Pan, J Z 2024, Archer : A human-labeled text-to-SQL dataset with arithmetic, commonsense and hypothetical reasoning. in Y Graham, M Purver & M Purver (eds), Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics. pp. 94-111, The 18th Conference of the European Chapter of the Association for Computational Linguistics, St. Julian\u2019s, Malta, 17/03/24. https://doi.org/10.18653/v1/2024.eacl-long.6","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.eacl-long.6","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.eacl-long.6","pdf_url":"https://aclanthology.org/2024.eacl-long.6.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":"Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G373773752","display_name":null,"funder_award_id":"EP/S022481/1","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"}],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411630271.pdf","grobid_xml":"https://content.openalex.org/works/W4411630271.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3035583586","https://openalex.org/W4320165839","https://openalex.org/W2151799802","https://openalex.org/W2196562041","https://openalex.org/W4385488510","https://openalex.org/W2073302931","https://openalex.org/W3206107299","https://openalex.org/W3082691151","https://openalex.org/W4287633646","https://openalex.org/W4378501473"],"abstract_inverted_index":{"We":[0],"present":[1],"Archer,":[2],"a":[3,42,66,84,239,247],"challenging":[4],"bilingual":[5],"textto-SQL":[6],"dataset":[7,40],"specific":[8],"to":[9,49,99,176],"complex":[10],"reasoning,":[11],"including":[12],"arithmetic,":[13],"commonsense":[14],"and":[15,22,108,111,190],"hypothetical":[16],"reasoning.It":[17],"contains":[18],"1,042":[19,23],"English":[20,34],"questions":[21],"Chinese":[24],"questions,":[25],"along":[26,186],"with":[27,65,187],"521":[28],"unique":[29],"SQL":[30],"queries,":[31],"covering":[32],"20":[33,37],"databases":[35],"across":[36],"domains.Notably,":[38],"this":[39,91],"demonstrates":[41],"significantly":[43],"higher":[44,233],"level":[45],"of":[46,61,238,246],"complexity":[47],"compared":[48],"existing":[50],"publicly":[51],"available":[52],"datasets.Our":[53],"evaluation":[54],"shows":[55],"that":[56],"Archer":[57,79,82],"challenges":[58],"the":[59,70,96,159,173,235,243],"capabilities":[60],"current":[62],"state-of-the-art":[63],"models,":[64],"high-ranked":[67],"model":[68],"on":[69,78,217],"Spider":[71],"leaderboard":[72],"achieving":[73],"only":[74],"6.73%":[75],"execution":[76],"accuracy":[77],"test":[80],"set.Thus,":[81],"presents":[83],"significant":[85],"challenge":[86],"for":[87],"future":[88],"research":[89],"in":[90,166],"field.Which":[92],"4-cylinder":[93,168],"car":[94,241],"needs":[95,172],"most":[97,174],"fuel":[98,125,175],"drive":[100,177],"300":[101,113,132,178,197],"miles?List":[102],"how":[103,181],"many":[104,182],"gallons":[105,183],"it":[106,184],"needs,":[107,185],"its":[109,188],"make":[110,189],"model.":[112],"Commonsense":[114,153],"Knowledge:":[115],"Fuel":[116],"used":[117],"is":[118,234],"calculated":[119],"by":[120,124,158],"divding":[121],"distance":[122],"driven":[123],"consumption.SELECT":[126],"B.":[127],"Make,":[128],"B.Model,":[129,194],"1.0":[130,195],"*":[131,196],"/":[133,198],"mpg":[134,149,199,225],"AS":[135,200,265],"n_gallon":[136,201],"FROM":[137,202,255,267],"cars_data":[138,203,256,268],"A":[139,204,257,269],"JOIN":[140,205,210,258,270],"car_names":[141,206,259,271],"B":[142,207,260,272],"ON":[143,208,213,261,273],"A.Id=B.MakeId":[144],"WHERE":[145,263,275],"cylinders=\"4\"":[146],"ORDER":[147,223],"BY":[148,224],"ASC":[150,226],"LIMIT":[151,227],"1":[152,228],"ReasoningIf":[154],"all":[155,167],"cars":[156],"produced":[157],"Daimler":[160],"Benz":[161],"company":[162],"have":[163],"4cylinders,":[164],"then":[165],"cars,":[169],"which":[170],"one":[171],"miles?Please":[179],"list":[180],"model.300":[191],"SELECT":[192,250],"B.Make,":[193],"A.id=B.makeid":[209,262,274],"model_list":[211],"C":[212],"B.model=C.modelJOIN":[214],"car_makers":[215],"D":[216],"C.maker=D.idWHERE":[218],"D.fullname=\"Daimler":[219],"Benz\"":[220],"or":[221],"A.cylinders=\"4\"":[222],"Hypothetical":[229],"Reasoning":[230],"How":[231],"much":[232],"maximum":[236,244],"power":[237,245],"BMW":[240],"than":[242],"Fiat":[248],"car?":[249],"MAX(horsepower)":[251],"-(SELECT":[252],"MAX":[253],"(horsepower)":[254],"B.model=\"fiat\")":[264],"diff":[266],"B.model=\"bmw\"":[276]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}