{"id":"https://openalex.org/W4284710241","doi":"https://doi.org/10.1145/3510003.3510050","title":"What do they capture?","display_name":"What do they capture?","publication_year":2022,"publication_date":"2022-05-21","ids":{"openalex":"https://openalex.org/W4284710241","doi":"https://doi.org/10.1145/3510003.3510050"},"language":"en","primary_location":{"id":"doi:10.1145/3510003.3510050","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3510003.3510050","pdf_url":null,"source":{"id":"https://openalex.org/S4363608872","display_name":"Proceedings of the 44th International Conference on 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 44th International Conference on Software Engineering","raw_type":"proceedings-article"},"type":"article","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/A5101555948","display_name":"Yao Wan","orcid":"https://orcid.org/0000-0001-6937-4180"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yao Wan","raw_affiliation_strings":["Huazhong University of Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042501292","display_name":"Wei Zhao","orcid":"https://orcid.org/0000-0003-1497-9312"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhao","raw_affiliation_strings":["Huazhong University of Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, China","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412598","display_name":"Hongyu Zhang","orcid":"https://orcid.org/0000-0002-3063-9425"},"institutions":[{"id":"https://openalex.org/I78757542","display_name":"University of Newcastle Australia","ror":"https://ror.org/00eae9z71","country_code":"AU","type":"education","lineage":["https://openalex.org/I78757542"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hongyu Zhang","raw_affiliation_strings":["University of Newcastle, Australia"],"affiliations":[{"raw_affiliation_string":"University of Newcastle, Australia","institution_ids":["https://openalex.org/I78757542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053058502","display_name":"Yulei Sui","orcid":"https://orcid.org/0000-0002-9510-6574"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yulei Sui","raw_affiliation_strings":["University of Technology Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"University of Technology Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051512158","display_name":"Guandong Xu","orcid":"https://orcid.org/0000-0003-4493-6663"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Guandong Xu","raw_affiliation_strings":["University of Technology Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"University of Technology Sydney, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022262922","display_name":"Hai Jin","orcid":"https://orcid.org/0000-0002-3934-7605"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hai Jin","raw_affiliation_strings":["Huazhong University of Science and Technology, China"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101555948"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":9.3651,"has_fulltext":false,"cited_by_count":66,"citation_normalized_percentile":{"value":0.98655799,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2377","last_page":"2388"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9934999942779541,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9908999800682068,"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/computer-science","display_name":"Computer science","score":0.8112691640853882},{"id":"https://openalex.org/keywords/abstract-syntax-tree","display_name":"Abstract syntax tree","score":0.7786522507667542},{"id":"https://openalex.org/keywords/abstract-syntax","display_name":"Abstract syntax","score":0.6143549084663391},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5973069667816162},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5477815866470337},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.5104078650474548},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49051254987716675},{"id":"https://openalex.org/keywords/code-review","display_name":"Code review","score":0.4879586100578308},{"id":"https://openalex.org/keywords/kpi-driven-code-analysis","display_name":"KPI-driven code analysis","score":0.4707028865814209},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.46819648146629333},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.4664596617221832},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4628201425075531},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4486531913280487},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.4381333887577057},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.41090816259384155},{"id":"https://openalex.org/keywords/static-program-analysis","display_name":"Static program analysis","score":0.3869093656539917},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.24657639861106873},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.08199620246887207},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.08111715316772461}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8112691640853882},{"id":"https://openalex.org/C58646249","wikidata":"https://www.wikidata.org/wiki/Q127380","display_name":"Abstract syntax tree","level":3,"score":0.7786522507667542},{"id":"https://openalex.org/C114408938","wikidata":"https://www.wikidata.org/wiki/Q333373","display_name":"Abstract syntax","level":3,"score":0.6143549084663391},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5973069667816162},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5477815866470337},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.5104078650474548},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49051254987716675},{"id":"https://openalex.org/C150292731","wikidata":"https://www.wikidata.org/wiki/Q1342704","display_name":"Code review","level":5,"score":0.4879586100578308},{"id":"https://openalex.org/C121957198","wikidata":"https://www.wikidata.org/wiki/Q14365593","display_name":"KPI-driven code analysis","level":5,"score":0.4707028865814209},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.46819648146629333},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.4664596617221832},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4628201425075531},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4486531913280487},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.4381333887577057},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.41090816259384155},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.3869093656539917},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.24657639861106873},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.08199620246887207},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.08111715316772461},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3510003.3510050","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3510003.3510050","pdf_url":null,"source":{"id":"https://openalex.org/S4363608872","display_name":"Proceedings of the 44th International Conference on 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 44th International Conference on Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1586088471","display_name":null,"funder_award_id":"No. 62102157","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W2045812729","https://openalex.org/W2143861926","https://openalex.org/W2602856279","https://openalex.org/W2750779823","https://openalex.org/W2794601162","https://openalex.org/W2798569372","https://openalex.org/W2887364112","https://openalex.org/W2946417913","https://openalex.org/W2962739339","https://openalex.org/W2962784628","https://openalex.org/W2964150020","https://openalex.org/W2964204621","https://openalex.org/W2970120757","https://openalex.org/W2972498556","https://openalex.org/W2988217457","https://openalex.org/W2994865335","https://openalex.org/W3038035611","https://openalex.org/W3091730360","https://openalex.org/W3093464584","https://openalex.org/W3098605233","https://openalex.org/W3107793421","https://openalex.org/W3118485687","https://openalex.org/W4245255589","https://openalex.org/W4293508270"],"related_works":["https://openalex.org/W3153702491","https://openalex.org/W2969257295","https://openalex.org/W3008981372","https://openalex.org/W2789660410","https://openalex.org/W3006945192","https://openalex.org/W2034209539","https://openalex.org/W1976804602","https://openalex.org/W4400488007","https://openalex.org/W2206096527","https://openalex.org/W4386788767"],"abstract_inverted_index":{"Recently,":[0],"many":[1],"pre-trained":[2,59,92,167],"language":[3,93,146],"models":[4,37,68,94,147,168],"for":[5,22,95,200],"source":[6,96],"code":[7,16,24,29,31,34,60,97,149,156,170,194,202],"have":[8,44,171],"been":[9],"proposed":[10],"to":[11,87,188],"model":[12],"the":[13,112,139,152,158,172,190,196],"context":[14],"of":[15,57,91,142,148,155,161,169,174,178,193,198],"and":[17,33,41,43,70,100,115],"serve":[18],"as":[19,28],"a":[20,82],"basis":[21],"downstream":[23],"intelligence":[25],"tasks":[26],"such":[27],"completion,":[30],"search,":[32],"summarization.":[35],"These":[36],"leverage":[38],"masked":[39],"pre-training":[40,199],"Transformer":[42,163],"achieved":[45],"promising":[46],"results.":[47],"However,":[48],"currently":[49],"there":[50],"is":[51,63],"still":[52],"little":[53],"progress":[54],"regarding":[55],"interpretability":[56],"existing":[58],"models.":[61],"It":[62],"not":[64],"clear":[65],"why":[66],"these":[67],"work":[69],"what":[71],"feature":[72],"correlations":[73],"they":[74],"can":[75,150],"capture.":[76],"In":[77],"this":[78,123],"paper,":[79],"we":[80],"conduct":[81],"thorough":[83],"structural":[84],"analysis":[85],"aiming":[86],"provide":[88],"an":[89],"interpretation":[90],"(e.g.,":[98],"CodeBERT,":[99],"GraphCodeBERT)":[101],"from":[102],"three":[103],"distinctive":[104],"perspectives:":[105],"(1)":[106,134],"attention":[107],"analysis,":[108,122],"(2)":[109,144],"probing":[110],"on":[111],"word":[113],"embedding,":[114],"(3)":[116,165],"syntax":[117,140,153,176,191],"tree":[118],"induction.":[119],"Through":[120],"comprehensive":[121],"paper":[124],"reveals":[125],"several":[126],"insightful":[127],"findings":[128,181],"that":[129,183],"may":[130,185],"inspire":[131],"future":[132],"studies:":[133],"Attention":[135],"aligns":[136],"strongly":[137],"with":[138],"structure":[141,154,192],"code.":[143,179],"Pre-training":[145],"preserve":[151],"in":[157],"intermediate":[159],"representations":[160],"each":[162],"layer.":[164],"The":[166],"ability":[173],"inducing":[175],"trees":[177],"Theses":[180],"suggest":[182],"it":[184],"be":[186],"helpful":[187],"incorporate":[189],"into":[195],"process":[197],"better":[201],"representations.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":28},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":3}],"updated_date":"2026-03-17T09:09:15.849793","created_date":"2025-10-10T00:00:00"}
