{"id":"https://openalex.org/W4384026730","doi":"https://doi.org/10.1109/msr59073.2023.00035","title":"Enriching Source Code with Contextual Data for Code Completion Models: An Empirical Study","display_name":"Enriching Source Code with Contextual Data for Code Completion Models: An Empirical Study","publication_year":2023,"publication_date":"2023-05-01","ids":{"openalex":"https://openalex.org/W4384026730","doi":"https://doi.org/10.1109/msr59073.2023.00035"},"language":"en","primary_location":{"id":"doi:10.1109/msr59073.2023.00035","doi":"https://doi.org/10.1109/msr59073.2023.00035","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msr59073.2023.00035","pdf_url":null,"source":{"id":"https://openalex.org/S7407088599","display_name":"International Conference on Mining Software Repositories (MSR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2023 IEEE/ACM 20th International Conference on Mining Software Repositories (MSR)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2304.12269","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074259780","display_name":"Tim van Dam","orcid":"https://orcid.org/0009-0009-3659-7068","observed_orcids":["https://orcid.org/0009-0009-3659-7068"]},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Tim van Dam","raw_affiliation_strings":["Delft University of Technology, Delft, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064355563","display_name":"Maliheh Izadi","orcid":"https://orcid.org/0000-0001-5093-5523","observed_orcids":["https://orcid.org/0000-0001-5093-5523"]},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Maliheh Izadi","raw_affiliation_strings":["Delft University of Technology, Delft, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090401584","display_name":"Arie Van Deursen A","orcid":"https://orcid.org/0000-0003-4850-3312","observed_orcids":["https://orcid.org/0000-0003-4850-3312"]},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Arie van Deursen","raw_affiliation_strings":["Delft University of Technology, Delft, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":3.976,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.95600743,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"170","last_page":"182"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":1.0,"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":1.0,"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":0.0,"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":0.0,"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/code-completion","display_name":"code completion","score":0.8339999914169312},{"id":"https://openalex.org/keywords/contextual-information","display_name":"contextual information","score":0.6940000057220459},{"id":"https://openalex.org/keywords/type-annotations","display_name":"type annotations","score":0.9369999766349792},{"id":"https://openalex.org/keywords/code-comments","display_name":"code comments","score":0.7749999761581421},{"id":"https://openalex.org/keywords/unixcoder","display_name":"UniXcoder","score":0.906000018119812},{"id":"https://openalex.org/keywords/code-readability","display_name":"code readability","score":0.49000000953674316},{"id":"https://openalex.org/keywords/transformer","display_name":"transformer models","score":0.3889999985694885}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8337974548339844},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5762941837310791},{"id":"https://openalex.org/C150292731","wikidata":"https://www.wikidata.org/wiki/Q1342704","display_name":"Code review","level":5,"score":0.5634713172912598},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.5388903021812439},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5178594589233398},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4375571012496948},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.42131489515304565},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.4124703109264374},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.394142210483551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39220428466796875},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36007165908813477},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3485388159751892},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.30037108063697815},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.2807251811027527},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.275877445936203},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.14191675186157227},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/msr59073.2023.00035","doi":"https://doi.org/10.1109/msr59073.2023.00035","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msr59073.2023.00035","pdf_url":null,"source":{"id":"https://openalex.org/S7407088599","display_name":"International Conference on Mining Software Repositories (MSR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"2023 IEEE/ACM 20th International Conference on Mining Software Repositories (MSR)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2304.12269","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.12269","pdf_url":"https://arxiv.org/pdf/2304.12269","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,"listed_in":[],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:tudelft.nl:uuid:69c13738-0f23-42d5-845d-3312381e3b94","doi":null,"is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:69c13738-0f23-42d5-845d-3312381e3b94","pdf_url":"https://repository.tudelft.nl/file/File_39386f25-a9c4-401a-940e-a43723ba7e62","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference paper"},{"id":"doi:10.48550/arxiv.2304.12269","doi":"https://doi.org/10.48550/arxiv.2304.12269","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2304.12269","pdf_url":null,"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,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2304.12269","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2304.12269","pdf_url":"https://arxiv.org/pdf/2304.12269","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,"listed_in":[],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4384026730.pdf","grobid_xml":"https://content.openalex.org/works/W4384026730.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W1588719663","https://openalex.org/W1994616650","https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2142112143","https://openalex.org/W2154652894","https://openalex.org/W2287501982","https://openalex.org/W2344444819","https://openalex.org/W2626778328","https://openalex.org/W2767824559","https://openalex.org/W2798362442","https://openalex.org/W2896457183","https://openalex.org/W2899384793","https://openalex.org/W2903709763","https://openalex.org/W2914501196","https://openalex.org/W2920812691","https://openalex.org/W2954950681","https://openalex.org/W2963341956","https://openalex.org/W2965373594","https://openalex.org/W2981852735","https://openalex.org/W2995502120","https://openalex.org/W2999616200","https://openalex.org/W3008088841","https://openalex.org/W3025298766","https://openalex.org/W3025993830","https://openalex.org/W3030163527","https://openalex.org/W3093464584","https://openalex.org/W3094439486","https://openalex.org/W3098605233","https://openalex.org/W3126675481","https://openalex.org/W3136309015","https://openalex.org/W3175705212","https://openalex.org/W3177813494","https://openalex.org/W3185059256","https://openalex.org/W3189653670","https://openalex.org/W3194752080","https://openalex.org/W3198685994","https://openalex.org/W4221166942","https://openalex.org/W4224060952","https://openalex.org/W4225809611","https://openalex.org/W4226279206","https://openalex.org/W4226285354","https://openalex.org/W4299358159","https://openalex.org/W4308021859","https://openalex.org/W4376606797","https://openalex.org/W4385270051","https://openalex.org/W4394638297","https://openalex.org/W6766673545","https://openalex.org/W6810681707","https://openalex.org/W6898505805","https://openalex.org/W6948415067","https://openalex.org/W7119001154"],"related_works":["https://openalex.org/W4394744510","https://openalex.org/W3121707215","https://openalex.org/W4405601526","https://openalex.org/W4376606906","https://openalex.org/W4226350810","https://openalex.org/W4402671782","https://openalex.org/W4381571810","https://openalex.org/W3160765131","https://openalex.org/W3216242986","https://openalex.org/W3189653670"],"abstract_inverted_index":{"Transformer-based":[0],"pre-trained":[1,74],"models":[2,77,127,160,180,211],"have":[3,28],"recently":[4],"achieved":[5],"great":[6],"results":[7],"in":[8,22,112,183],"solving":[9],"many":[10,27],"software":[11],"engineering":[12],"tasks":[13],"including":[14],"automatic":[15],"code":[16,43,62,75,82,103,110],"completion":[17,111,119],"which":[18],"is":[19],"a":[20,23],"staple":[21],"developer\u2019s":[24],"toolkit.":[25],"While":[26],"striven":[29],"to":[30,45,58,64,147,156,228],"improve":[31,229],"the":[32,38,42,71,79,106,142,152,169,179,184,213,230],"code-understanding":[33],"abilities":[34],"of":[35,73,81,94,186,234],"such":[36,210],"models,":[37],"opposite":[39],"\u2013":[40,47],"making":[41,61,200],"easier":[44,63],"understand":[46,65,102],"has":[48],"not":[49],"been":[50],"properly":[51],"investigated.":[52],"In":[53],"this":[54],"study,":[55],"we":[56,108,140,176,198],"aim":[57],"answer":[59],"whether":[60],"through":[66],"using":[67],"contextual":[68,96],"data":[69,215],"improves":[70],"performance":[72],"language":[76,126],"for":[78,128],"task":[80],"completion.":[83],"We":[84],"consider":[85],"type":[86,164],"annotations":[87,165],"and":[88,117,120,124,133,150,216,220,232],"comments":[89,188],"as":[90],"two":[91,113],"common":[92],"forms":[93],"additional":[95],"information":[97],"that":[98,178],"often":[99],"help":[100],"developers":[101],"better.":[104],"For":[105,174],"experiments,":[107],"study":[109],"granularity":[114],"levels;":[115],"token":[116],"line":[118],"take":[121],"three":[122],"recent":[123],"large-scale":[125],"source":[129],"code:":[130],"UniXcoder,":[131],"CodeGPT,":[132],"InCoder":[134],"with":[135,190],"five":[136],"evaluation":[137],"metrics.":[138],"Finally,":[139],"perform":[141,161,181],"Wilcoxon":[143],"Signed":[144],"Rank":[145],"test":[146],"gauge":[148],"significance":[149],"measure":[151],"effect":[153,170,192],"size.":[154],"Contrary":[155],"our":[157,196],"expectations,":[158],"all":[159],"better":[162,182],"if":[163],"are":[166,172],"removed":[167],"(albeit":[168],"sizes":[171],"small).":[173],"comments,":[175],"find":[177],"presence":[185],"multi-line":[187],"(again":[189],"small":[191],"sizes).":[193],"Based":[194],"on":[195],"observations,":[197],"recommend":[199],"proper":[201],"design":[202],"choices":[203],"when":[204],"training,":[205],"fine-tuning,":[206],"or":[207],"simply":[208],"selecting":[209],"given":[212],"intended":[214],"application.":[217],"Better":[218],"evaluations":[219],"multimodal":[221],"techniques":[222],"can":[223],"also":[224],"be":[225],"further":[226],"investigated":[227],"practicality":[231],"accuracy":[233],"auto-completions.":[235]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2023-07-13T00:00:00"}