{"id":"https://openalex.org/W4281787155","doi":"https://doi.org/10.1145/3514221.3517878","title":"PreQR: Pre-training Representation for SQL Understanding","display_name":"PreQR: Pre-training Representation for SQL Understanding","publication_year":2022,"publication_date":"2022-06-10","ids":{"openalex":"https://openalex.org/W4281787155","doi":"https://doi.org/10.1145/3514221.3517878"},"language":"en","primary_location":{"id":"doi:10.1145/3514221.3517878","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3514221.3517878","pdf_url":null,"source":{"id":"https://openalex.org/S4363608845","display_name":"Proceedings of the 2022 International Conference on Management of Data","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Management of Data","raw_type":"proceedings-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/A5072228670","display_name":"Xiu Tang","orcid":"https://orcid.org/0000-0001-8611-0283"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiu Tang","raw_affiliation_strings":["Zhejiang University, HangZhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, HangZhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064646829","display_name":"Sai Wu","orcid":"https://orcid.org/0000-0002-1866-9197"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sai Wu","raw_affiliation_strings":["Zhejiang University, HangZhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, HangZhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026532752","display_name":"Mingli Song","orcid":"https://orcid.org/0000-0003-2621-6048"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingli Song","raw_affiliation_strings":["Zhejiang University, HangZhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, HangZhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089530055","display_name":"Shanshan Ying","orcid":"https://orcid.org/0000-0003-2338-2139"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shanshan Ying","raw_affiliation_strings":["Alibaba Group, HangZhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, HangZhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450470","display_name":"Feifei Li","orcid":"https://orcid.org/0009-0003-0770-5775"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feifei Li","raw_affiliation_strings":["Alibaba Group, HangZhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, HangZhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100389286","display_name":"Gang Chen","orcid":"https://orcid.org/0000-0002-7483-0045"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Chen","raw_affiliation_strings":["Zhejiang University, HangZhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, HangZhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5072228670"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":5.1801,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.97142857,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"204","last_page":"216"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"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/T11719","display_name":"Data Quality and Management","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"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/T10683","display_name":"Mass Spectrometry Techniques and Applications","score":0.9894999861717224,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9864000082015991,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8798779249191284},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.5822787880897522},{"id":"https://openalex.org/keywords/query-by-example","display_name":"Query by Example","score":0.5742142796516418},{"id":"https://openalex.org/keywords/database-schema","display_name":"Database schema","score":0.4984903335571289},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.46998870372772217},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.4640706181526184},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.45928099751472473},{"id":"https://openalex.org/keywords/view","display_name":"View","score":0.4435420632362366},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.422288715839386},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3857431411743164},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.35067716240882874},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3338802456855774},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32458633184432983},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.2643570899963379},{"id":"https://openalex.org/keywords/database-design","display_name":"Database design","score":0.22267818450927734},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.12258294224739075}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8798779249191284},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.5822787880897522},{"id":"https://openalex.org/C194222762","wikidata":"https://www.wikidata.org/wiki/Q114486","display_name":"Query by Example","level":4,"score":0.5742142796516418},{"id":"https://openalex.org/C30775581","wikidata":"https://www.wikidata.org/wiki/Q632285","display_name":"Database schema","level":3,"score":0.4984903335571289},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.46998870372772217},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.4640706181526184},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.45928099751472473},{"id":"https://openalex.org/C54239708","wikidata":"https://www.wikidata.org/wiki/Q1329910","display_name":"View","level":3,"score":0.4435420632362366},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.422288715839386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3857431411743164},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35067716240882874},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3338802456855774},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32458633184432983},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.2643570899963379},{"id":"https://openalex.org/C148840519","wikidata":"https://www.wikidata.org/wiki/Q1049878","display_name":"Database design","level":2,"score":0.22267818450927734},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.12258294224739075},{"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},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3514221.3517878","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3514221.3517878","pdf_url":null,"source":{"id":"https://openalex.org/S4363608845","display_name":"Proceedings of the 2022 International Conference on Management of Data","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 International Conference on Management of Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3682670028","display_name":null,"funder_award_id":"61872315, 62050099","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1623444038","https://openalex.org/W1985554184","https://openalex.org/W2068245803","https://openalex.org/W2101105183","https://openalex.org/W2102166438","https://openalex.org/W2116341502","https://openalex.org/W2250539671","https://openalex.org/W2295144739","https://openalex.org/W2396309311","https://openalex.org/W2604314403","https://openalex.org/W2801426799","https://openalex.org/W2886983157","https://openalex.org/W2890585661","https://openalex.org/W2911489562","https://openalex.org/W2948513753","https://openalex.org/W2962739339","https://openalex.org/W2963026768","https://openalex.org/W2963661253","https://openalex.org/W2970148517","https://openalex.org/W2970851599","https://openalex.org/W2998249308","https://openalex.org/W3029535034","https://openalex.org/W3097225903","https://openalex.org/W3099273181","https://openalex.org/W3173587790","https://openalex.org/W3178212073","https://openalex.org/W4205922070","https://openalex.org/W4253103663","https://openalex.org/W6675727724"],"related_works":["https://openalex.org/W319014924","https://openalex.org/W2374912898","https://openalex.org/W2375340541","https://openalex.org/W644450836","https://openalex.org/W2406556739","https://openalex.org/W2554271401","https://openalex.org/W2970853428","https://openalex.org/W4244527061","https://openalex.org/W2152149667","https://openalex.org/W2186703450"],"abstract_inverted_index":{"Recently,":[0],"the":[1,8,31,73,86,102,113,130,140],"learning-based":[2,28,144],"models":[3,145],"are":[4],"shown":[5],"to":[6,39,77,84,95,116],"outperform":[7],"conventional":[9],"methods":[10,29],"for":[11,34],"many":[12],"database":[13,48,97,148],"tasks":[14],"such":[15,58],"as":[16],"cardinality":[17],"estimation,":[18],"join":[19],"order":[20],"selection":[21],"and":[22,51,89],"performance":[23],"tuning.":[24],"However,":[25],"most":[26],"existing":[27,143],"adopt":[30],"one-hot":[32,131],"encoding":[33,132],"SQL":[35,66,78,106],"query":[36,87,135],"representation,":[37],"unable":[38],"catch":[40],"complicated":[41],"semantic":[42],"context,":[43],"e.g.":[44],"structure":[45],"of":[46,54,142],"query,":[47],"schema":[49,98,120],"definition":[50],"distribution":[52],"variance":[53],"columns.":[55],"To":[56],"address":[57],"above":[59],"problem,":[60],"we":[61],"propose":[62,81],"a":[63,91],"novel":[64],"pre-trained":[65],"representation":[67,75,136],"model,":[68],"called":[69],"PreQR,":[70],"which":[71],"extends":[72],"language":[74],"approach":[76],"queries.":[79],"We":[80],"an":[82],"automaton":[83],"encode":[85,96],"structures,":[88],"apply":[90],"graph":[92],"neural":[93],"network":[94],"information":[99],"conditioned":[100],"on":[101,124,146],"query.":[103],"A":[104],"new":[105],"encoder":[107],"is":[108],"then":[109],"established":[110],"by":[111],"adopting":[112],"attention":[114],"mechanism":[115],"support":[117],"on-the-fly":[118],"query-aware":[119],"linking.":[121],"Experimental":[122],"results":[123],"real":[125],"datasets":[126],"show":[127],"that":[128],"replacing":[129],"with":[133],"our":[134],"can":[137],"significantly":[138],"improve":[139],"performances":[141],"several":[147],"tasks.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":5}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}