{"id":"https://openalex.org/W4409920472","doi":"https://doi.org/10.1145/3731752","title":"Bipartite-Grammar\u2013Aware Pretraining for XML-SQL Code Updating","display_name":"Bipartite-Grammar\u2013Aware Pretraining for XML-SQL Code Updating","publication_year":2025,"publication_date":"2025-04-29","ids":{"openalex":"https://openalex.org/W4409920472","doi":"https://doi.org/10.1145/3731752"},"language":"en","primary_location":{"id":"doi:10.1145/3731752","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731752","pdf_url":null,"source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-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/A5034794084","display_name":"Qingyuan Liang","orcid":"https://orcid.org/0000-0002-1697-3451"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qingyuan Liang","raw_affiliation_strings":["Key Lab of HCST (PKU), MOE, SCS, Peking University, Beijing, China","Key Lab of HCST (PKU), MOE; SCS, Peking University, China"],"affiliations":[{"raw_affiliation_string":"Key Lab of HCST (PKU), MOE, SCS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Key Lab of HCST (PKU), MOE; SCS, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047965752","display_name":"Zeyu Sun","orcid":"https://orcid.org/0000-0002-9990-9120"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeyu Sun","raw_affiliation_strings":["National Key Laboratory of Space Integrated Information System, Institute of Software, Chinese Academy of Sciences, Beijing, China","National Key Laboratory of Space Integrated Information System, Institute of Software, Chinese Academy of Sciences, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory of Space Integrated Information System, Institute of Software, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]},{"raw_affiliation_string":"National Key Laboratory of Space Integrated Information System, Institute of Software, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054377991","display_name":"Yifan Zhao","orcid":"https://orcid.org/0000-0002-2035-0791"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Zhao","raw_affiliation_strings":["Key Lab of HCST (PKU), MOE, SCS, Peking University, Beijing, China","Key Lab of HCST (PKU), MOE; SCS, Peking University, China"],"affiliations":[{"raw_affiliation_string":"Key Lab of HCST (PKU), MOE, SCS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Key Lab of HCST (PKU), MOE; SCS, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115076660","display_name":"Zhihao Gong","orcid":"https://orcid.org/0009-0003-5318-8473"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihao Gong","raw_affiliation_strings":["Key Lab of HCST (PKU), MOE, SCS, Peking University, Beijing, China","Key Lab of HCST (PKU), MOE; SCS, Peking University, China"],"affiliations":[{"raw_affiliation_string":"Key Lab of HCST (PKU), MOE, SCS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Key Lab of HCST (PKU), MOE; SCS, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084069443","display_name":"Guoqing Wang","orcid":"https://orcid.org/0009-0000-5208-4750"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoqing Wang","raw_affiliation_strings":["Key Lab of HCST (PKU), MOE, SCS, Peking University, Beijing, China","Key Lab of HCST (PKU), MOE; SCS, Peking University, China"],"affiliations":[{"raw_affiliation_string":"Key Lab of HCST (PKU), MOE, SCS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Key Lab of HCST (PKU), MOE; SCS, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009476223","display_name":"Yizhou Chen","orcid":"https://orcid.org/0000-0003-1821-3170"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizhou Chen","raw_affiliation_strings":["Key Lab of HCST (PKU), MOE, SCS, Peking University, Beijing, China","Key Lab of HCST (PKU), MOE; SCS, Peking University, China"],"affiliations":[{"raw_affiliation_string":"Key Lab of HCST (PKU), MOE, SCS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Key Lab of HCST (PKU), MOE; SCS, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100388576","display_name":"Lu Zhang","orcid":"https://orcid.org/0000-0001-8304-7055"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Zhang","raw_affiliation_strings":["Key Lab of HCST (PKU), MOE, SCS, Peking University, Beijing, China","Key Lab of HCST (PKU), MOE; SCS, Peking University, China"],"affiliations":[{"raw_affiliation_string":"Key Lab of HCST (PKU), MOE, SCS, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Key Lab of HCST (PKU), MOE; SCS, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038623189","display_name":"Guangtai Liang","orcid":"https://orcid.org/0009-0004-2454-1706"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangtai Liang","raw_affiliation_strings":["Huawei Technologies Co Ltd, Beijing, China","Huawei Cloud, China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co Ltd, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Cloud, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012567911","display_name":"Qianxiang Wang","orcid":"https://orcid.org/0000-0002-6598-0041"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianxiang Wang","raw_affiliation_strings":["Huawei Technologies Co Ltd, Beijing, China","Huawei Cloud, China"],"affiliations":[{"raw_affiliation_string":"Huawei Technologies Co Ltd, Beijing, China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Cloud, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5034794084"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":5.7685,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.95317771,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"35","issue":"2","first_page":"1","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9952999949455261,"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":0.9952999949455261,"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/T10126","display_name":"Logic, programming, and type systems","score":0.9919000267982483,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.986299991607666,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.8796582221984863},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5612819790840149},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.5024459362030029},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.4858788847923279},{"id":"https://openalex.org/keywords/sql","display_name":"SQL","score":0.45159053802490234},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3546805679798126},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.22781458497047424},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0998266339302063}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8796582221984863},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5612819790840149},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.5024459362030029},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.4858788847923279},{"id":"https://openalex.org/C510870499","wikidata":"https://www.wikidata.org/wiki/Q47607","display_name":"SQL","level":2,"score":0.45159053802490234},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3546805679798126},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.22781458497047424},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0998266339302063},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731752","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731752","pdf_url":null,"source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1540525488","https://openalex.org/W1566499845","https://openalex.org/W1593271688","https://openalex.org/W1848790451","https://openalex.org/W1971017525","https://openalex.org/W1981097903","https://openalex.org/W2006061474","https://openalex.org/W2037392323","https://openalex.org/W2127386193","https://openalex.org/W2144373616","https://openalex.org/W2534253848","https://openalex.org/W2600463316","https://openalex.org/W2772008372","https://openalex.org/W2774343269","https://openalex.org/W2967262539","https://openalex.org/W2972082064","https://openalex.org/W3093060337","https://openalex.org/W3129831491","https://openalex.org/W3161903544","https://openalex.org/W3193682477","https://openalex.org/W4283314525","https://openalex.org/W4285168059","https://openalex.org/W4308643152","https://openalex.org/W4313547604","https://openalex.org/W4391558404","https://openalex.org/W4394769280","https://openalex.org/W4394769313","https://openalex.org/W4400484371","https://openalex.org/W4403579163"],"related_works":["https://openalex.org/W2003932708","https://openalex.org/W1967424056","https://openalex.org/W2284877871","https://openalex.org/W2138102289","https://openalex.org/W868043274","https://openalex.org/W2513523087","https://openalex.org/W1187916458","https://openalex.org/W2373861055","https://openalex.org/W2063575861","https://openalex.org/W4320802139"],"abstract_inverted_index":{"The":[0],"e":[1],"X":[2],"tensible":[3],"M":[4],"arkup":[5],"L":[6],"anguage":[7],"(XML)":[8],"is":[9],"a":[10,35,69,129,174,287],"file":[11],"format":[12],"widely":[13],"used":[14],"for":[15,38,64,180],"data":[16],"transmission":[17],"in":[18,28,147],"modern":[19],"software":[20],"development.":[21],"In":[22,112],"recent":[23],"years,":[24],"embedding":[25],"SQL":[26],"statements":[27],"XML":[29],"files":[30],"(i.e.,":[31,163],"XML-SQL)":[32],"has":[33,87],"become":[34],"popular":[36],"way":[37,71],"developing":[39,81],"applications":[40],"with":[41,293],"database":[42],"access":[43],"capability.":[44],"Typically,":[45],"XML-SQL":[46,82,85,149,158,193,199,246,283],"code":[47,62,66,86,94,110,130,144,189,200],"snippets":[48],"demonstrate":[49],"similar":[50],"functionalities":[51],"and":[52,76,133,159,209,229],"structures,":[53],"leading":[54,102],"to":[55,72,98,103,117,139,172,191,220,238,263,276,279,297],"repetitive":[56],"programming":[57,161,165],"work.":[58],"Therefore,":[59],"leveraging":[60],"pre-trained":[61,93,109],"models":[63,95,190],"automated":[65],"generation":[67,145,290],"presents":[68],"promising":[70],"alleviate":[73],"duplicated":[74],"efforts":[75],"enhance":[77],"the":[78,119,135,142,148,154,185,192,198,222,230,235,264,282],"efficiency":[79],"of":[80,107,121,157,187,204,225,245],"code.":[83,247],"However,":[84],"strong":[88],"domain-specific":[89,124,243],"characteristics":[90,156],"that":[91,252,273],"general":[92,108],"typically":[96],"struggle":[97],"fully":[99,280],"harness,":[100],"thereby":[101,183],"limited":[104],"overall":[105],"performance":[106,146],"models.":[111],"this":[113,123],"article,":[114],"we":[115,127,152,196,214],"aim":[116],"address":[118],"challenge":[120],"handling":[122],"knowledge.":[125],"First,":[126],"propose":[128],"updating":[131],"task":[132],"construct":[134],"corresponding":[136],"TwinXSQL":[137],"dataset":[138],"better":[140,239],"evaluate":[141],"model\u2019s":[143],"domain.":[150,194],"Then,":[151],"leverage":[153],"common":[155],"other":[160],"languages":[162,166],"all":[164],"impose":[167],"grammar":[168],"constraints":[169],"on":[170],"behavior)":[171],"design":[173],"bipartite-grammar\u2013aware":[175],"training":[176],"framework":[177],"(named":[178],"BGA)":[179],"unsupervised":[181],"pre-training,":[182,213],"improving":[184],"transfer":[186],"general-purpose":[188],"Specifically,":[195],"divide":[197],"into":[201],"two":[202],"types":[203],"grammatical":[205,227],"components:":[206],"structure":[207],"components":[208,228],"value":[210],"components.":[211],"During":[212],"undertake":[215],"three":[216],"tasks,":[217],"each":[218],"designed":[219],"learn":[221,281],"internal":[223],"information":[224],"these":[226],"relationships":[231],"between":[232],"them,":[233],"enabling":[234],"pre-training":[236],"process":[237],"incorporate":[240],"previously":[241],"unlearned":[242],"knowledge":[244],"Our":[248],"experimental":[249],"results":[250],"show":[251],"our":[253,270,298],"trained":[254],"model":[255],"XSQLT5-base":[256,299],"(220M)":[257,300],"improves":[258],"accuracy":[259,291],"by":[260],"13.8%":[261],"compared":[262,296],"similarly":[265],"sized":[266],"CodeT5-base":[267],"(220M).":[268],"Additionally,":[269],"experiments":[271],"reveal":[272],"ChatGPT,":[274],"due":[275],"its":[277],"inability":[278],"domain":[284],"knowledge,":[285],"achieves":[286],"much":[288],"lower":[289],"even":[292],"few-shot":[294],"samples":[295],"model.":[301]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-01-22T23:29:09.771500","created_date":"2025-10-10T00:00:00"}
