{"id":"https://openalex.org/W2938075706","doi":"https://doi.org/10.1109/msr.2019.00015","title":"Semantic Source Code Models Using Identifier Embeddings","display_name":"Semantic Source Code Models Using Identifier Embeddings","publication_year":2019,"publication_date":"2019-05-01","ids":{"openalex":"https://openalex.org/W2938075706","doi":"https://doi.org/10.1109/msr.2019.00015","mag":"2938075706"},"language":"en","primary_location":{"id":"doi:10.1109/msr.2019.00015","doi":"https://doi.org/10.1109/msr.2019.00015","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msr.2019.00015","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":"2019 IEEE/ACM 16th 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/1904.06929","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082898464","display_name":"Vasiliki Efstathiou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I73142707","display_name":"Athens University of Economics and Business","ror":"https://ror.org/03s262162","country_code":"GR","type":"education","lineage":["https://openalex.org/I73142707"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Vasiliki Efstathiou","raw_affiliation_strings":["Athens University of Economics and Business"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Athens University of Economics and Business","institution_ids":["https://openalex.org/I73142707"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021948425","display_name":"Diomidis D. Spinellis","orcid":"https://orcid.org/0000-0003-4231-1897","observed_orcids":["https://orcid.org/0000-0003-4231-1897"]},"institutions":[{"id":"https://openalex.org/I73142707","display_name":"Athens University of Economics and Business","ror":"https://ror.org/03s262162","country_code":"GR","type":"education","lineage":["https://openalex.org/I73142707"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Diomidis Spinellis","raw_affiliation_strings":["Athens University of Economics and Business"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Athens University of Economics and Business","institution_ids":["https://openalex.org/I73142707"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I73142707"],"apc_list":null,"apc_paid":null,"fwci":2.8605,"has_fulltext":true,"cited_by_count":28,"citation_normalized_percentile":{"value":0.92098622,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"29","last_page":"33"},"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/fasttext","display_name":"FastText","score":0.6980000138282776},{"id":"https://openalex.org/keywords/code-search","display_name":"code search","score":0.6990000009536743},{"id":"https://openalex.org/keywords/code-reuse","display_name":"code reuse","score":0.9010000228881836},{"id":"https://openalex.org/keywords/open-source-software-repositories","display_name":"open-source repositories","score":0.7160000205039978},{"id":"https://openalex.org/keywords/coding-conventions","display_name":"coding conventions","score":0.8939999938011169},{"id":"https://openalex.org/keywords/software-maintenance","display_name":"software maintenance","score":0.460999995470047}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8711683750152588},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.6937943696975708},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6155388355255127},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.599260687828064},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.5573738217353821},{"id":"https://openalex.org/C51929080","wikidata":"https://www.wikidata.org/wiki/Q2425187","display_name":"Codebase","level":3,"score":0.5308189392089844},{"id":"https://openalex.org/C121957198","wikidata":"https://www.wikidata.org/wiki/Q14365593","display_name":"KPI-driven code analysis","level":5,"score":0.47444427013397217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4434043765068054},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.43705421686172485},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.4249238967895508},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4246494174003601},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3686627149581909},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3278096914291382},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.3173450827598572},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.20177298784255981}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/msr.2019.00015","doi":"https://doi.org/10.1109/msr.2019.00015","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msr.2019.00015","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":"2019 IEEE/ACM 16th International Conference on Mining Software Repositories (MSR)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1904.06929","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.06929","pdf_url":"https://arxiv.org/pdf/1904.06929","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2954246333","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1904.06929v1","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1904.06929","doi":"https://doi.org/10.48550/arxiv.1904.06929","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1904.06929","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":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1904.06929","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1904.06929","pdf_url":"https://arxiv.org/pdf/1904.06929","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G8059770990","display_name":"Developer-Centric Knowledge Mining from Large Open-Source Software Repositories","funder_award_id":"732223","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2938075706.pdf","grobid_xml":"https://content.openalex.org/works/W2938075706.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W658020064","https://openalex.org/W1614298861","https://openalex.org/W1972141422","https://openalex.org/W2014116953","https://openalex.org/W2103018059","https://openalex.org/W2141682682","https://openalex.org/W2142403498","https://openalex.org/W2148190602","https://openalex.org/W2168565044","https://openalex.org/W2238078713","https://openalex.org/W2242083635","https://openalex.org/W2250539671","https://openalex.org/W2257123346","https://openalex.org/W2293111794","https://openalex.org/W2298765043","https://openalex.org/W2474318526","https://openalex.org/W2493916176","https://openalex.org/W2511803001","https://openalex.org/W2513738415","https://openalex.org/W2516621648","https://openalex.org/W2553051037","https://openalex.org/W2559885217","https://openalex.org/W2587676558","https://openalex.org/W2593675739","https://openalex.org/W2605202003","https://openalex.org/W2620994026","https://openalex.org/W2728974883","https://openalex.org/W2738442629","https://openalex.org/W2740220421","https://openalex.org/W2741705590","https://openalex.org/W2742131885","https://openalex.org/W2754629507","https://openalex.org/W2780932362","https://openalex.org/W2788784374","https://openalex.org/W2795143051","https://openalex.org/W2882319491","https://openalex.org/W2884229567","https://openalex.org/W2962772361","https://openalex.org/W2963617989","https://openalex.org/W2963667932","https://openalex.org/W2963935794","https://openalex.org/W2964325845","https://openalex.org/W3146720657","https://openalex.org/W3148057751","https://openalex.org/W4250687526","https://openalex.org/W4300546131","https://openalex.org/W6742200057","https://openalex.org/W6748304040","https://openalex.org/W6804089450","https://openalex.org/W6949296359"],"related_works":["https://openalex.org/W2942322914","https://openalex.org/W2980256670","https://openalex.org/W6893954902","https://openalex.org/W3005276469","https://openalex.org/W2148190602","https://openalex.org/W2795143051","https://openalex.org/W3041033573","https://openalex.org/W3152617716","https://openalex.org/W3045289171","https://openalex.org/W3177625213"],"abstract_inverted_index":{"The":[0,117],"emergence":[1],"of":[2,19,32,77,83,96,192,205,211],"online":[3],"open":[4],"source":[5,22,68,160],"repositories":[6],"in":[7,16,39,44,67,93,166,169,196],"the":[8,17,63,94,141,171,183,190,193,197,206,212],"recent":[9,42],"years":[10],"has":[11],"led":[12],"to":[13,29,57,149],"an":[14,37],"explosion":[15],"volume":[18],"openly":[20],"available":[21],"code,":[23,161],"coupled":[24],"with":[25,41],"metadata":[26],"that":[27],"relate":[28],"a":[30,123,137],"variety":[31],"software":[33,48],"development":[34],"activities.":[35],"As":[36],"effect,":[38],"line":[40],"advances":[43],"machine":[45],"learning":[46,127],"research,":[47],"maintenance":[49],"activities":[50],"are":[51,119],"switching":[52],"from":[53,136],"symbolic":[54],"formal":[55],"methods":[56],"data-driven":[58],"methods.":[59],"In":[60],"this":[61,89],"context,":[62],"rich":[64],"semantics":[65],"hidden":[66],"code":[69,78,84,102,142],"identifiers":[70],"provide":[71],"opportunities":[72],"for":[73,104,126,144],"building":[74],"semantic":[75],"representations":[76,103],"which":[79],"can":[80],"assist":[81],"tasks":[82],"search":[85],"and":[86,115,159,189,208],"reuse.":[87],"To":[88],"end,":[90],"we":[91,175,187,201],"deliver":[92],"form":[95],"pretrained":[97],"vector":[98],"space":[99],"models,":[100],"distributed":[101],"six":[105],"popular":[106],"programming":[107,139,173],"languages,":[108],"namely,":[109],"Java,":[110],"Python,":[111],"PHP,":[112],"C,":[113],"C++,":[114],"C#.":[116],"models":[118,147,207],"produced":[120],"using":[121],"fastText,":[122],"state-of-the-art":[124],"library":[125],"word":[128],"representations.":[129],"Each":[130],"model":[131],"is":[132],"trained":[133],"on":[134],"data":[135,184],"single":[138],"language;":[140],"mined":[143],"producing":[145],"all":[146],"amounts":[148],"over":[150],"13.000":[151],"repositories.":[152],"We":[153,177],"indicate":[154],"dissimilarities":[155],"between":[156,170],"natural":[157],"language":[158],"as":[162,164],"well":[163],"variations":[165],"coding":[167],"conventions":[168],"different":[172],"languages":[174],"processed.":[176],"describe":[178],"how":[179],"these":[180],"heterogeneities":[181],"guided":[182],"preprocessing":[185],"decisions":[186],"took":[188],"selection":[191],"training":[194],"parameters":[195],"released":[198],"models.":[199,213],"Finally,":[200],"propose":[202],"potential":[203],"applications":[204],"discuss":[209],"limitations":[210]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2019-04-25T00:00:00"}