{"id":"https://openalex.org/W4226463316","doi":"https://doi.org/10.1145/3506696","title":"<scp>XCode</scp> : Towards Cross-Language Code Representation with Large-Scale Pre-Training","display_name":"<scp>XCode</scp> : Towards Cross-Language Code Representation with Large-Scale Pre-Training","publication_year":2022,"publication_date":"2022-04-09","ids":{"openalex":"https://openalex.org/W4226463316","doi":"https://doi.org/10.1145/3506696"},"language":"en","primary_location":{"id":"doi:10.1145/3506696","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3506696","pdf_url":null,"source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-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/A5079229946","display_name":"Zehao Lin","orcid":"https://orcid.org/0000-0002-4726-7867"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zehao Lin","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":"https://orcid.org/0000-0002-4726-7867","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022944148","display_name":"Guodun Li","orcid":null},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guodun Li","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100749004","display_name":"Jingfeng Zhang","orcid":"https://orcid.org/0000-0003-3491-8074"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingfeng Zhang","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104037923","display_name":"Yue Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yue Deng","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100956227","display_name":"Xiangji Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangji Zeng","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343699","display_name":"Yin Zhang","orcid":"https://orcid.org/0000-0001-6986-4227"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yin Zhang","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"last","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":false,"raw_author_name":"Yao Wan","raw_affiliation_strings":["School of Computer Sci. and Tech., Huazhong University of Science and Technology, Wuhan, Hubei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Sci. and Tech., Huazhong University of Science and Technology, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.78,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.95270228,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"31","issue":"3","first_page":"1","last_page":"44"},"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":0.9952999949455261,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9799000024795532,"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/computer-science","display_name":"Computer science","score":0.8840973377227783},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.6370021104812622},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.5936444401741028},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.5717238783836365},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5371072888374329},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5181207060813904},{"id":"https://openalex.org/keywords/kpi-driven-code-analysis","display_name":"KPI-driven code analysis","score":0.5042985677719116},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4448951780796051},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4352518320083618},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.42980748414993286},{"id":"https://openalex.org/keywords/abstract-syntax-tree","display_name":"Abstract syntax tree","score":0.42851269245147705},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.3655228316783905},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.28359824419021606},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.24169576168060303},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.21006518602371216}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8840973377227783},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6370021104812622},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.5936444401741028},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.5717238783836365},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5371072888374329},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5181207060813904},{"id":"https://openalex.org/C121957198","wikidata":"https://www.wikidata.org/wiki/Q14365593","display_name":"KPI-driven code analysis","level":5,"score":0.5042985677719116},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4448951780796051},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4352518320083618},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.42980748414993286},{"id":"https://openalex.org/C58646249","wikidata":"https://www.wikidata.org/wiki/Q127380","display_name":"Abstract syntax tree","level":3,"score":0.42851269245147705},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.3655228316783905},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.28359824419021606},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.24169576168060303},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.21006518602371216},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3506696","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3506696","pdf_url":null,"source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6399999856948853,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G7039412344","display_name":null,"funder_award_id":"62072399 and U19B2042","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8363725921","display_name":null,"funder_award_id":"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"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":76,"referenced_works":["https://openalex.org/W1498436455","https://openalex.org/W1538131130","https://openalex.org/W1731081199","https://openalex.org/W1832693441","https://openalex.org/W1956340063","https://openalex.org/W2064675550","https://openalex.org/W2079887492","https://openalex.org/W2105816471","https://openalex.org/W2131774270","https://openalex.org/W2146957318","https://openalex.org/W2149788502","https://openalex.org/W2194775991","https://openalex.org/W2282866165","https://openalex.org/W2513738415","https://openalex.org/W2531207078","https://openalex.org/W2583649498","https://openalex.org/W2591591831","https://openalex.org/W2602856279","https://openalex.org/W2606722458","https://openalex.org/W2772617084","https://openalex.org/W2794601162","https://openalex.org/W2808279976","https://openalex.org/W2884276923","https://openalex.org/W2887255581","https://openalex.org/W2887364112","https://openalex.org/W2888557792","https://openalex.org/W2888651608","https://openalex.org/W2897767292","https://openalex.org/W2899171197","https://openalex.org/W2907778768","https://openalex.org/W2931212643","https://openalex.org/W2947683321","https://openalex.org/W2949266019","https://openalex.org/W2956017828","https://openalex.org/W2963081964","https://openalex.org/W2963247703","https://openalex.org/W2963364041","https://openalex.org/W2963736842","https://openalex.org/W2963767194","https://openalex.org/W2963935794","https://openalex.org/W2964150020","https://openalex.org/W2964350391","https://openalex.org/W2964935470","https://openalex.org/W2968179027","https://openalex.org/W2971261034","https://openalex.org/W2972082064","https://openalex.org/W2972758308","https://openalex.org/W2979271470","https://openalex.org/W2980998888","https://openalex.org/W2993743533","https://openalex.org/W2999343753","https://openalex.org/W3000135256","https://openalex.org/W3005598269","https://openalex.org/W3005951744","https://openalex.org/W3010181709","https://openalex.org/W3018591247","https://openalex.org/W3022560936","https://openalex.org/W3027616835","https://openalex.org/W3034172739","https://openalex.org/W3041012898","https://openalex.org/W3088611441","https://openalex.org/W3090867931","https://openalex.org/W3091995628","https://openalex.org/W3093415205","https://openalex.org/W3098121686","https://openalex.org/W3098605233","https://openalex.org/W3102527112","https://openalex.org/W3106692695","https://openalex.org/W3146720657","https://openalex.org/W3162962341","https://openalex.org/W3173450168","https://openalex.org/W3198188208","https://openalex.org/W3208790591","https://openalex.org/W3212088361","https://openalex.org/W4205918858","https://openalex.org/W4245415816"],"related_works":["https://openalex.org/W4284703357","https://openalex.org/W1486852150","https://openalex.org/W4200321676","https://openalex.org/W3172857546","https://openalex.org/W2390371246","https://openalex.org/W2361120086","https://openalex.org/W1909375798","https://openalex.org/W2525896035","https://openalex.org/W4389438938","https://openalex.org/W4282813445"],"abstract_inverted_index":{"Source":[0],"code":[1,18,24,37,61,148,156,219,221,249,259],"representation":[2,38,121,260],"learning":[3,73],"is":[4],"the":[5,33,44,64,82,88,161,176,184,189,202,241],"basis":[6],"of":[7,35,47,84,232,243,268],"applying":[8],"artificial":[9],"intelligence":[10],"to":[11,31,98,133,143,180,188,199],"many":[12,27,76],"software":[13],"engineering":[14],"tasks":[15,78,265],"such":[16],"as":[17],"clone":[19,222],"detection,":[20,223],"algorithm":[21],"classification,":[22],"and":[23,139,195,224],"summarization.":[25],"Recently,":[26],"works":[28],"have":[29],"tried":[30],"improve":[32],"performance":[34],"source":[36,60,147,203,218],"from":[39,63,81,183],"various":[40],"perspectives,":[41],"e.g.,":[42],"introducing":[43],"structural":[45,89],"information":[46],"programs":[48],"into":[49],"latent":[50],"representation.":[51],"However,":[52],"when":[53],"dealing":[54],"with":[55,122,235],"rapidly":[56],"expanded":[57],"unlabeled":[58],"cross-language":[59,215,248],"datasets":[62],"Internet,":[65],"there":[66],"are":[67],"still":[68,79],"two":[69],"issues.":[70],"Firstly,":[71],"deep":[72],"models":[74,150,187,194],"for":[75],"code-specific":[77],"suffer":[80],"lack":[83],"high-quality":[85],"labels.":[86],"Secondly,":[87],"differences":[90],"among":[91],"programming":[92,164,233],"languages":[93,101],"make":[94],"it":[95],"more":[96],"difficult":[97],"process":[99],"multiple":[100,145,236,269],"in":[102,111,266],"a":[103,116,123,169,228],"single":[104],"neural":[105],"architecture.":[106],"To":[107,158],"address":[108],"these":[109],"issues,":[110],"this":[112],"article,":[113],"we":[114,131,166,207],"propose":[115,132,168],"novel":[117],"Cross":[118],"-language":[119],"Code":[120],"large-scale":[124],"pre-training":[125],"(":[126],"XCode":[127],")":[128],"method.":[129],"Concretely,":[130],"use":[134],"several":[135,258],"abstract":[136],"syntax":[137],"trees":[138],"ELMo-enhanced":[140],"variational":[141],"autoencoders":[142],"obtain":[144],"pre-trained":[146,186,193],"language":[149],"trained":[151],"on":[152,211,227,247,262],"about":[153],"1.5":[154],"million":[155],"snippets.":[157],"fully":[159],"utilize":[160],"knowledge":[162,182],"across":[163],"languages,":[165],"further":[167],"Shared":[170],"Encoder-Decoder":[171],"(SED)":[172],"architecture":[173],"which":[174],"uses":[175],"multi-teacher":[177],"single-student":[178],"method":[179],"transfer":[181],"aforementioned":[185],"distilled":[190],"SED.":[191],"The":[192],"SED":[196],"will":[197],"cooperate":[198],"better":[200,256],"represent":[201],"code.":[204],"For":[205],"evaluation,":[206],"examine":[208],"our":[209,244,252],"approach":[210,246,253],"three":[212],"typical":[213],"downstream":[214,264],"tasks,":[216],"i.e.,":[217],"translation,":[220],"code-to-code":[225],"search,":[226],"real-world":[229],"dataset":[230],"composed":[231],"exercises":[234],"solutions.":[237],"Experimental":[238],"results":[239],"demonstrate":[240],"effectiveness":[242],"proposed":[245],"representations.":[250],"Meanwhile,":[251],"performs":[254],"significantly":[255],"than":[257],"baselines":[261],"different":[263],"terms":[267],"automatic":[270],"evaluation":[271],"metrics.":[272]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
