{"id":"https://openalex.org/W3093464584","doi":"https://doi.org/10.1145/3468264.3468611","title":"Empirical study of transformers for source code","display_name":"Empirical study of transformers for source code","publication_year":2021,"publication_date":"2021-08-18","ids":{"openalex":"https://openalex.org/W3093464584","doi":"https://doi.org/10.1145/3468264.3468611","mag":"3093464584"},"language":"en","primary_location":{"id":"doi:10.1145/3468264.3468611","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3468264.3468611","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3468264.3468611","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3468264.3468611","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Nadezhda Chirkova","orcid":"https://orcid.org/0000-0001-8188-3391"},"institutions":[{"id":"https://openalex.org/I118501908","display_name":"National Research University Higher School of Economics","ror":"https://ror.org/055f7t516","country_code":"RU","type":"education","lineage":["https://openalex.org/I118501908"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Nadezhda Chirkova","raw_affiliation_strings":["HSE University, Russia"],"raw_orcid":"https://orcid.org/0000-0001-8188-3391","affiliations":[{"raw_affiliation_string":"HSE University, Russia","institution_ids":["https://openalex.org/I118501908"]}]},{"author_position":"last","author":{"id":null,"display_name":"Sergey Troshin","orcid":"https://orcid.org/0000-0002-8439-390X"},"institutions":[{"id":"https://openalex.org/I118501908","display_name":"National Research University Higher School of Economics","ror":"https://ror.org/055f7t516","country_code":"RU","type":"education","lineage":["https://openalex.org/I118501908"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Sergey Troshin","raw_affiliation_strings":["HSE University, Russia"],"raw_orcid":"https://orcid.org/0000-0002-8439-390X","affiliations":[{"raw_affiliation_string":"HSE University, Russia","institution_ids":["https://openalex.org/I118501908"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I118501908"],"apc_list":null,"apc_paid":null,"fwci":10.2292,"has_fulltext":true,"cited_by_count":54,"citation_normalized_percentile":{"value":0.98781176,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"703","last_page":"715"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9987000226974487,"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":0.9969000220298767,"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/source-code","display_name":"Source code","score":0.7523000240325928},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6610000133514404},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.4984000027179718},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.478300005197525},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.46959999203681946},{"id":"https://openalex.org/keywords/abstract-syntax","display_name":"Abstract syntax","score":0.45190000534057617}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.772599995136261},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.7523000240325928},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6610000133514404},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5062999725341797},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.4984000027179718},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.478300005197525},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.46959999203681946},{"id":"https://openalex.org/C114408938","wikidata":"https://www.wikidata.org/wiki/Q333373","display_name":"Abstract syntax","level":3,"score":0.45190000534057617},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3580000102519989},{"id":"https://openalex.org/C120012220","wikidata":"https://www.wikidata.org/wiki/Q1754533","display_name":"Source text","level":2,"score":0.35679998993873596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34709998965263367},{"id":"https://openalex.org/C2778095710","wikidata":"https://www.wikidata.org/wiki/Q6031225","display_name":"Information source (mathematics)","level":2,"score":0.32100000977516174},{"id":"https://openalex.org/C58646249","wikidata":"https://www.wikidata.org/wiki/Q127380","display_name":"Abstract syntax tree","level":3,"score":0.3100000023841858},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2736000120639801},{"id":"https://openalex.org/C2983685735","wikidata":"https://www.wikidata.org/wiki/Q5227355","display_name":"Data source","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3468264.3468611","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3468264.3468611","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3468264.3468611","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2010.07987","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.07987","pdf_url":"https://arxiv.org/pdf/2010.07987","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,"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"}],"best_oa_location":{"id":"doi:10.1145/3468264.3468611","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3468264.3468611","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3468264.3468611","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1476772921","display_name":null,"funder_award_id":"19-71-30020","funder_id":"https://openalex.org/F4320324099","funder_display_name":"Russian Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320324099","display_name":"Russian Science Foundation","ror":"https://ror.org/03y2gwe85"},{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3093464584.pdf","grobid_xml":"https://content.openalex.org/works/W3093464584.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2238673293","https://openalex.org/W2516621648","https://openalex.org/W2533695286","https://openalex.org/W2605202003","https://openalex.org/W2768572539","https://openalex.org/W2799855324","https://openalex.org/W2884276923","https://openalex.org/W2887364112","https://openalex.org/W2888557792","https://openalex.org/W2963341956","https://openalex.org/W2963355447","https://openalex.org/W2963925437","https://openalex.org/W2964194820","https://openalex.org/W2964772344","https://openalex.org/W2979792666","https://openalex.org/W2997847174","https://openalex.org/W3011564318","https://openalex.org/W3022049116","https://openalex.org/W3034689979","https://openalex.org/W3098605233","https://openalex.org/W6739901393"],"related_works":[],"abstract_inverted_index":{"Initially":[0],"developed":[1],"for":[2,12,51,144],"natural":[3,29],"language":[4],"processing":[5],"(NLP),":[6],"Transformers":[7,89,120],"are":[8,121],"now":[9],"widely":[10],"used":[11],"source":[13,22,31,56],"code":[14,23,32],"processing,":[15],"due":[16],"to":[17,28,69,90,123],"the":[18,39,42,86,134,139,146,149],"format":[19],"similarity":[20],"between":[21],"and":[24,72,105,108,132],"text.":[25],"In":[26,76],"contrast":[27],"language,":[30],"is":[33,63],"strictly":[34],"structured,":[35],"i.e.,":[36],"it":[37],"follows":[38],"syntax":[40],"of":[41,60,85,88,137,148],"programming":[43],"language.":[44],"Several":[45],"recent":[46],"works":[47,62],"develop":[48],"Transformer":[49],"modifications":[50,112],"capturing":[52],"syntactic":[53,92,130,140],"information":[54,93,131,141],"in":[55,94,113],"code.":[57],"The":[58],"drawback":[59],"these":[61],"that":[64,119],"they":[65],"do":[66],"not":[67],"compare":[68],"each":[70],"other":[71],"consider":[73,98],"different":[74,95,110],"tasks.":[75,96],"this":[77],"work,":[78],"we":[79],"conduct":[80],"a":[81,114],"thorough":[82],"empirical":[83],"study":[84],"capabilities":[87],"utilize":[91],"We":[97,117],"three":[99],"tasks":[100],"(code":[101],"completion,":[102],"function":[103],"naming":[104],"bug":[106],"fixing)":[107],"re-implement":[109],"syntax-capturing":[111],"unified":[115],"framework.":[116],"show":[118],"able":[122],"make":[124],"meaningful":[125],"predictions":[126],"based":[127],"purely":[128],"on":[129],"underline":[133],"best":[135],"practices":[136],"taking":[138],"into":[142],"account":[143],"improving":[145],"performance":[147],"model.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2020-10-22T00:00:00"}