{"id":"https://openalex.org/W4308731473","doi":"https://doi.org/10.1145/3540250.3549162","title":"NatGen: generative pre-training by \u201cnaturalizing\u201d source code","display_name":"NatGen: generative pre-training by \u201cnaturalizing\u201d source code","publication_year":2022,"publication_date":"2022-11-07","ids":{"openalex":"https://openalex.org/W4308731473","doi":"https://doi.org/10.1145/3540250.3549162"},"language":"en","primary_location":{"id":"doi:10.1145/3540250.3549162","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3540250.3549162","pdf_url":null,"source":{"id":"https://openalex.org/S4363608883","display_name":"Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","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 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"},"type":"conference-paper","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/A5074368173","display_name":"Saikat Chakraborty","orcid":"https://orcid.org/0000-0002-6889-7171"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saikat Chakraborty","raw_affiliation_strings":["Columbia University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072573553","display_name":"Toufique Ahmed","orcid":"https://orcid.org/0000-0002-4427-1350"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Toufique Ahmed","raw_affiliation_strings":["University of California at Davis, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California at Davis, USA","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064527453","display_name":"Yangruibo Ding","orcid":"https://orcid.org/0000-0003-3224-6876"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yangruibo Ding","raw_affiliation_strings":["Columbia University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036744986","display_name":"Pr\u00e9mkumar D\u00e9vanbu","orcid":"https://orcid.org/0000-0002-4346-5276"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Premkumar T. Devanbu","raw_affiliation_strings":["University of California at Davis, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California at Davis, USA","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064541855","display_name":"Baishakhi Ray","orcid":"https://orcid.org/0000-0003-3406-5235"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Baishakhi Ray","raw_affiliation_strings":["Columbia University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":101,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"18","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9912999868392944,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9736999869346619,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.8109438419342041},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.6747748255729675},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.644416332244873},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.6399709582328796},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5452998876571655},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.525359570980072},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5009365081787109},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.4725370407104492},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4699955880641937},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4501412808895111},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.41457778215408325},{"id":"https://openalex.org/keywords/kpi-driven-code-analysis","display_name":"KPI-driven code analysis","score":0.41374778747558594},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.3199852705001831},{"id":"https://openalex.org/keywords/static-program-analysis","display_name":"Static program analysis","score":0.24761876463890076},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.24196207523345947},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.1450101137161255}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8109438419342041},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6747748255729675},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.644416332244873},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.6399709582328796},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5452998876571655},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.525359570980072},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5009365081787109},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.4725370407104492},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4699955880641937},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4501412808895111},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.41457778215408325},{"id":"https://openalex.org/C121957198","wikidata":"https://www.wikidata.org/wiki/Q14365593","display_name":"KPI-driven code analysis","level":5,"score":0.41374778747558594},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3199852705001831},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.24761876463890076},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.24196207523345947},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.1450101137161255},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3540250.3549162","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3540250.3549162","pdf_url":null,"source":{"id":"https://openalex.org/S4363608883","display_name":"Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","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 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7087383019","display_name":null,"funder_award_id":"CCF-2107405, SHF-1845893, SHF-1414172, SHF-2107592, IIS-2221943","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1771830246","https://openalex.org/W2010608861","https://openalex.org/W2153887189","https://openalex.org/W2344444819","https://openalex.org/W2511803001","https://openalex.org/W2516621648","https://openalex.org/W2541061885","https://openalex.org/W2560647685","https://openalex.org/W2605202003","https://openalex.org/W2740130862","https://openalex.org/W2740220421","https://openalex.org/W2883915502","https://openalex.org/W2950434427","https://openalex.org/W2954823997","https://openalex.org/W2963499153","https://openalex.org/W2963935794","https://openalex.org/W2963943197","https://openalex.org/W2972082064","https://openalex.org/W2979792666","https://openalex.org/W3005855585","https://openalex.org/W3018033251","https://openalex.org/W3025298766","https://openalex.org/W3034689979","https://openalex.org/W3081159607","https://openalex.org/W3098605233","https://openalex.org/W3103499786","https://openalex.org/W3105735055","https://openalex.org/W3146720657","https://openalex.org/W3161997752","https://openalex.org/W3183962691","https://openalex.org/W3195156628","https://openalex.org/W3198685994","https://openalex.org/W4206312123","https://openalex.org/W4206756860","https://openalex.org/W4283751459","https://openalex.org/W4285177871","https://openalex.org/W6969431307"],"related_works":["https://openalex.org/W1486852150","https://openalex.org/W2904997879","https://openalex.org/W2390085541","https://openalex.org/W1990888989","https://openalex.org/W2149598945","https://openalex.org/W2316077753","https://openalex.org/W656101134","https://openalex.org/W2332490499","https://openalex.org/W3122369893","https://openalex.org/W2407476586"],"abstract_inverted_index":{"Pre-trained":[0],"Generative":[1],"Language":[2],"models":[3,28,52],"(e.g.,":[4,201],"PLBART,":[5],"CodeT5,":[6],"SPT-Code)":[7],"for":[8],"source":[9,68],"code":[10,23,38,92,163,165,168,199],"yielded":[11],"strong":[12],"results":[13],"on":[14,55],"several":[15],"tasks":[16],"in":[17,44,157],"the":[18,48,144],"past":[19],"few":[20],"years,":[21],"including":[22],"generation":[24],"and":[25,109,167,175,192,195],"translation.":[26],"These":[27],"have":[29],"adopted":[30],"varying":[31],"pre-training":[32,57,64],"objectives":[33],"to":[34,88,103,114,124,147],"learn":[35,146],"statistics":[36],"of":[37,50,67,99,107,136],"construction":[39],"from":[40],"very":[41],"large-scale":[42],"corpora":[43,135],"a":[45,62],"self-supervised":[46],"fashion;":[47],"success":[49],"pre-trained":[51,185],"largely":[53],"hinges":[54],"these":[56],"objectives.":[58],"This":[59],"paper":[60],"proposes":[61],"new":[63],"objective,":[65],"\u201cNaturalizing\u201d":[66],"code,":[69,108,130,138],"exploiting":[70],"code\u2019s":[71,82],"bimodal,":[72,83],"dual-channel":[73,84],"(formal":[74],"&":[75,150],"natural":[76,80,117,129],"channels)":[77],"nature.":[78],"Unlike":[79],"language,":[81],"nature":[85],"allows":[86],"us":[87],"generate":[89,125,151],"semantically":[90],"equivalent":[91],"at":[93,131,190,197],"scale.":[94],"We":[95,153,181],"introduce":[96,104],"six":[97],"classes":[98],"semantic":[100],"preserving":[101],"transformations":[102],"unnatural":[105],"forms":[106],"then":[110],"force":[111],"our":[112,155,184],"model":[113,145,156,186],"produce":[115],"more":[116,128],"original":[118],"programs":[119],"written":[120],"by":[121],"developers.":[122],"Learning":[123],"equivalent,":[126],"but":[127],"scale,":[132],"over":[133],"large":[134],"open-source":[137],"without":[139],"explicit":[140],"manual":[141],"supervision,":[142],"helps":[143],"both":[148],"ingest":[149],"code.":[152],"fine-tune":[154],"three":[158],"generative":[159],"Software":[160],"Engineering":[161],"tasks:":[162],"generation,":[164],"translation,":[166],"refinement":[169],"with":[170],"limited":[171],"human-curated":[172],"labeled":[173],"data":[174,203],"achieve":[176],"state-of-the-art":[177],"performance":[178],"rivaling":[179],"CodeT5.":[180],"show":[182],"that":[183],"is":[187],"especially":[188],"competitive":[189],"zero-shot":[191],"few-shot":[193],"learning,":[194],"better":[196],"learning":[198],"properties":[200],"syntax,":[202],"flow)":[204]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":34},{"year":2024,"cited_by_count":37},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}