{"id":"https://openalex.org/W3217001695","doi":"https://doi.org/10.1109/icsme52107.2021.00044","title":"Assessing Generalizability of CodeBERT","display_name":"Assessing Generalizability of CodeBERT","publication_year":2021,"publication_date":"2021-09-01","ids":{"openalex":"https://openalex.org/W3217001695","doi":"https://doi.org/10.1109/icsme52107.2021.00044","mag":"3217001695"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsme52107.2021.00044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ink.library.smu.edu.sg/context/sis_research/article/7857/viewcontent/288200a425.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100709810","display_name":"Xin Zhou","orcid":"https://orcid.org/0000-0003-0231-2895"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xin Zhou","raw_affiliation_strings":["School of Computing and Information Systems, Singapore Management University"],"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, Singapore Management University","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054365831","display_name":"DongGyun Han","orcid":"https://orcid.org/0000-0002-8599-2197"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"DongGyun Han","raw_affiliation_strings":["School of Computing and Information Systems, Singapore Management University"],"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, Singapore Management University","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081036622","display_name":"David Lo","orcid":"https://orcid.org/0000-0002-4367-7201"},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"David Lo","raw_affiliation_strings":["School of Computing and Information Systems, Singapore Management University"],"affiliations":[{"raw_affiliation_string":"School of Computing and Information Systems, Singapore Management University","institution_ids":["https://openalex.org/I79891267"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.564,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.999783,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"425","last_page":"436"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9999,"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":0.9999,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9776,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.977,"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/python","display_name":"Python","score":0.81141406},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical Research","score":0.48743728}],"concepts":[{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.9736673},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.84528553},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.81141406},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6149298},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.5661054},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5623375},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5284015},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.50846493},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.50827473},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.48743728},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.37597114},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsme52107.2021.00044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/context/sis_research/article/7857/viewcontent/288200a425.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":["Singapore Management University"],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/6854","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":["Singapore Management University"],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/context/sis_research/article/7857/viewcontent/288200a425.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":["Singapore Management University"],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":63,"referenced_works":["https://openalex.org/W1655956671","https://openalex.org/W1832693441","https://openalex.org/W2007705030","https://openalex.org/W2086511124","https://openalex.org/W2123024445","https://openalex.org/W2125279207","https://openalex.org/W2146338950","https://openalex.org/W2147386665","https://openalex.org/W2150874999","https://openalex.org/W2169669347","https://openalex.org/W2394841101","https://openalex.org/W2470673105","https://openalex.org/W2493916176","https://openalex.org/W2594760301","https://openalex.org/W2606150376","https://openalex.org/W2739996966","https://openalex.org/W2766875678","https://openalex.org/W2793157084","https://openalex.org/W2794601162","https://openalex.org/W2805788202","https://openalex.org/W2884001105","https://openalex.org/W2887364112","https://openalex.org/W2888651608","https://openalex.org/W2896457183","https://openalex.org/W2917037155","https://openalex.org/W2919115771","https://openalex.org/W2922006620","https://openalex.org/W2923014074","https://openalex.org/W2952230511","https://openalex.org/W2955991060","https://openalex.org/W2963026768","https://openalex.org/W2963159690","https://openalex.org/W2963392741","https://openalex.org/W2963548617","https://openalex.org/W2963748441","https://openalex.org/W2964150020","https://openalex.org/W2965373594","https://openalex.org/W2968179027","https://openalex.org/W2980708516","https://openalex.org/W2981851019","https://openalex.org/W2994865335","https://openalex.org/W2995179471","https://openalex.org/W2997049449","https://openalex.org/W3008086364","https://openalex.org/W3034549508","https://openalex.org/W3035882142","https://openalex.org/W3098044990","https://openalex.org/W3098281910","https://openalex.org/W3098605233","https://openalex.org/W3099636232","https://openalex.org/W3103170042","https://openalex.org/W3103981637","https://openalex.org/W3105867435","https://openalex.org/W3108032709","https://openalex.org/W3119507053","https://openalex.org/W3122473522","https://openalex.org/W3126675481","https://openalex.org/W3161997752","https://openalex.org/W4287824654","https://openalex.org/W4289292126","https://openalex.org/W4300427681","https://openalex.org/W4301582020","https://openalex.org/W4394638297"],"related_works":["https://openalex.org/W4225593417","https://openalex.org/W410723623","https://openalex.org/W2573498121","https://openalex.org/W2413243053","https://openalex.org/W2207495067","https://openalex.org/W2118717649","https://openalex.org/W2035068594","https://openalex.org/W2015341305","https://openalex.org/W1971398745","https://openalex.org/W1906486629"],"abstract_inverted_index":{"Pre-trained":[0],"models":[1,23,28],"like":[2],"BERT":[3],"have":[4],"achieved":[5],"strong":[6],"improvements":[7],"on":[8,46,73,146,203],"many":[9],"natural":[10,38],"language":[11,39,43],"processing":[12],"(NLP)":[13],"tasks,":[14,185],"showing":[15],"their":[16,154],"great":[17],"generalizability.":[18],"The":[19],"success":[20],"of":[21,121,128,163,179,201,234],"pre-trained":[22,27,45,61,83,94],"in":[24,79],"NLP":[25],"inspires":[26],"for":[29,36,63,221,240],"programming":[30,42],"language.":[31],"Recently,":[32],"CodeBERT,":[33],"a":[34,238],"model":[35],"both":[37],"(NL)":[40],"and":[41,106,153,165,207,225],"(PL),":[44],"code":[47,140,151,223,252],"search":[48,141,224,253],"dataset,":[49],"is":[50],"proposed.":[51],"Although":[52],"promising,":[53],"CodeBERT":[54,90,129,180,188,202,236],"has":[55,68],"not":[56],"been":[57,70],"evaluated":[58],"beyond":[59,92],"its":[60,82,93,134],"dataset":[62,148,162],"NL-PL":[64],"tasks.":[65,229],"Also,":[66],"it":[67,97,242],"only":[69],"shown":[71],"effective":[72],"two":[74,87],"tasks":[75,103],"that":[76],"are":[77],"close":[78],"nature":[80],"to":[81,99,130,175,181,189,250],"data.":[84,136],"This":[85],"raises":[86],"questions:":[88],"Can":[89,96],"generalize":[91,98],"data?":[95],"various":[100,182],"software":[101,183],"engineering":[102,184],"involving":[104],"NL":[105],"PL?":[107],"Our":[108,195],"work":[109],"answers":[110,166],"these":[111],"questions":[112,164],"by":[113],"performing":[114],"an":[115],"empirical":[116,196],"investigation":[117],"into":[118],"the":[119,126,139,177,190,199,204,222,231,235],"generalizability":[120,127,178,200],"CodeBERT.":[122],"First,":[123],"we":[124,143,186],"assess":[125,176],"datasets":[131],"other":[132],"than":[133,217],"pre-training":[135],"Specifically,":[137],"considering":[138],"task,":[142],"conduct":[144],"experiments":[145],"another":[147,161],"containing":[149],"Python":[150,172],"snippets":[152],"corresponding":[155],"documentation.":[156],"We":[157],"also":[158],"consider":[159],"yet":[160],"collected":[167],"from":[168],"Stack":[169],"Overflow":[170],"about":[171],"programming.":[173],"Second,":[174],"apply":[187],"just-in-time":[191,226],"defect":[192,227],"prediction":[193,228],"task.":[194,208],"results":[197],"support":[198],"additional":[205],"data":[206],"CodeBERT-based":[209],"solutions":[210,219],"can":[211],"achieve":[212],"higher":[213],"or":[214],"comparable":[215],"performance":[216,233],"specialized":[218,251],"designed":[220],"However,":[230],"superior":[232],"requires":[237,243],"tradeoff;":[239],"example,":[241],"much":[244],"more":[245],"computation":[246],"resources":[247],"as":[248],"compared":[249],"approaches.":[254]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3217001695","counts_by_year":[{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1}],"updated_date":"2024-12-26T18:19:11.171230","created_date":"2021-12-06"}