{"id":"https://openalex.org/W4320060335","doi":"https://doi.org/10.1109/icdm54844.2022.00050","title":"Contrastive Code-Comment Pre-training","display_name":"Contrastive Code-Comment Pre-training","publication_year":2022,"publication_date":"2022-11-01","ids":{"openalex":"https://openalex.org/W4320060335","doi":"https://doi.org/10.1109/icdm54844.2022.00050"},"language":"en","primary_location":{"id":"doi:10.1109/icdm54844.2022.00050","doi":"https://doi.org/10.1109/icdm54844.2022.00050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm54844.2022.00050","pdf_url":null,"source":{"id":"https://openalex.org/S4210214883","display_name":"Proceedings","issn_l":"1550-4786","issn":["1550-4786","2374-8486"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Data Mining (ICDM)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","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/A5060854400","display_name":"Xiaohuan Pei","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiaohuan Pei","raw_affiliation_strings":["The University of Sydney,School of Computer Science, Faculty of Engineering,Sydney,Australia","School of Computer Science, Faculty of Engineering, The University of Sydney, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Sydney,School of Computer Science, Faculty of Engineering,Sydney,Australia","institution_ids":["https://openalex.org/I129604602"]},{"raw_affiliation_string":"School of Computer Science, Faculty of Engineering, The University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029813674","display_name":"Daochang Liu","orcid":"https://orcid.org/0000-0002-9279-7912","observed_orcids":["https://orcid.org/0000-0002-9279-7912"]},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Daochang Liu","raw_affiliation_strings":["The University of Sydney,School of Computer Science, Faculty of Engineering,Sydney,Australia","School of Computer Science, Faculty of Engineering, The University of Sydney, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Sydney,School of Computer Science, Faculty of Engineering,Sydney,Australia","institution_ids":["https://openalex.org/I129604602"]},{"raw_affiliation_string":"School of Computer Science, Faculty of Engineering, The University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100566162","display_name":"Qian Luo","orcid":"https://orcid.org/0000-0002-1819-6043","observed_orcids":["https://orcid.org/0000-0002-1819-6043","https://orcid.org/0009-0001-0723-0269"]},"institutions":[{"id":"https://openalex.org/I4405259049","display_name":"Shanghai Qi Zhi Institute","ror":"https://ror.org/01n14yn69","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4405259049"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luo Qian","raw_affiliation_strings":["Shanghai Qi Zhi Institute, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Qi Zhi Institute, Shanghai, China","institution_ids":["https://openalex.org/I4405259049"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001529504","display_name":"Chang Xu","orcid":"https://orcid.org/0000-0002-4756-0609","observed_orcids":["https://orcid.org/0000-0002-4756-0609"]},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chang Xu","raw_affiliation_strings":["The University of Sydney,School of Computer Science, Faculty of Engineering,Sydney,Australia","School of Computer Science, Faculty of Engineering, The University of Sydney, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Sydney,School of Computer Science, Faculty of Engineering,Sydney,Australia","institution_ids":["https://openalex.org/I129604602"]},{"raw_affiliation_string":"School of Computer Science, Faculty of Engineering, The University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.447,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62969462,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"398","last_page":"407"},"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":9.999999747378752e-05,"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/T10533","display_name":"Teaching and Learning Programming","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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-comments","display_name":"code comments","score":0.7160000205039978},{"id":"https://openalex.org/keywords/contrastive-learning","display_name":"contrastive learning","score":0.9639999866485596},{"id":"https://openalex.org/keywords/multimodal-representation","display_name":"multimodal representation","score":0.6370000243186951},{"id":"https://openalex.org/keywords/code-search","display_name":"code search","score":0.5609999895095825},{"id":"https://openalex.org/keywords/code-clone-detection","display_name":"code clone detection","score":0.9620000123977661},{"id":"https://openalex.org/keywords/cross-lingual-transfer","display_name":"cross-lingual transfer","score":0.6819999814033508},{"id":"https://openalex.org/keywords/program-comprehension","display_name":"program comprehension","score":0.3529999852180481}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8523790836334229},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5393945574760437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5107283592224121},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5107142925262451},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.5103735327720642},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5093420743942261},{"id":"https://openalex.org/C114408938","wikidata":"https://www.wikidata.org/wiki/Q333373","display_name":"Abstract syntax","level":3,"score":0.47227156162261963},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.45555999875068665},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.44649872183799744},{"id":"https://openalex.org/C58646249","wikidata":"https://www.wikidata.org/wiki/Q127380","display_name":"Abstract syntax tree","level":3,"score":0.4100446105003357},{"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:10.1109/icdm54844.2022.00050","doi":"https://doi.org/10.1109/icdm54844.2022.00050","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdm54844.2022.00050","pdf_url":null,"source":{"id":"https://openalex.org/S4210214883","display_name":"Proceedings","issn_l":"1550-4786","issn":["1550-4786","2374-8486"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Data Mining (ICDM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2065053490","https://openalex.org/W2128782367","https://openalex.org/W2130942839","https://openalex.org/W2247864914","https://openalex.org/W2511803001","https://openalex.org/W2626778328","https://openalex.org/W2741705590","https://openalex.org/W2781491433","https://openalex.org/W2794601162","https://openalex.org/W2887364112","https://openalex.org/W2896457183","https://openalex.org/W2908510526","https://openalex.org/W2955426500","https://openalex.org/W2963341956","https://openalex.org/W2965373594","https://openalex.org/W2971246534","https://openalex.org/W2995259046","https://openalex.org/W2995333547","https://openalex.org/W3014339000","https://openalex.org/W3021393209","https://openalex.org/W3035027743","https://openalex.org/W3038476992","https://openalex.org/W3086007799","https://openalex.org/W3098044990","https://openalex.org/W3098605233","https://openalex.org/W3119507053","https://openalex.org/W3120793869","https://openalex.org/W3126095862","https://openalex.org/W3131648208","https://openalex.org/W3135367836","https://openalex.org/W3137158245","https://openalex.org/W3153233475","https://openalex.org/W3162689995","https://openalex.org/W3170092793","https://openalex.org/W3177813494","https://openalex.org/W3180353325","https://openalex.org/W3198685994","https://openalex.org/W3198948396","https://openalex.org/W4206291441","https://openalex.org/W4225576545","https://openalex.org/W4241645538","https://openalex.org/W4394638297","https://openalex.org/W6754601402","https://openalex.org/W6766673545","https://openalex.org/W7119001154","https://openalex.org/W7151510318"],"related_works":["https://openalex.org/W7024969177","https://openalex.org/W2921999611","https://openalex.org/W3008088841","https://openalex.org/W4308731473","https://openalex.org/W4391937149","https://openalex.org/W4221143516","https://openalex.org/W4391591817","https://openalex.org/W3198685994","https://openalex.org/W4387560999","https://openalex.org/W4403593660"],"abstract_inverted_index":{"Pre-trained":[0],"models":[1,182],"for":[2,40,132],"Natural":[3],"Languages":[4,15],"(NL)":[5],"have":[6,71],"been":[7],"recently":[8],"shown":[9],"to":[10,13,92,156,226],"transfer":[11],"well":[12,208],"Programming":[14],"(PL)":[16],"and":[17,32,50,65,69,75,105,114,122,146,204,216,248],"largely":[18],"benefit":[19],"different":[20,72],"intelligence":[21],"code-related":[22,186],"tasks,":[23],"such":[24],"as":[25,207,209],"code":[26,33,112,145,202,205],"search,":[27],"clone":[28],"detection,":[29],"programming":[30,41,104,214,229,251],"translation":[31,215],"document":[34,217],"generation.":[35,218],"However,":[36],"existing":[37],"pre-trained":[38,181,257],"methods":[39,247],"languages":[42],"are":[43,126],"mainly":[44],"conducted":[45],"by":[46,97,119,149],"masked":[47],"language":[48,116,230,252],"modeling":[49],"next":[51],"sentence":[52],"prediction":[53],"at":[54,262],"token":[55],"or":[56],"graph":[57],"levels.":[58],"This":[59],"restricted":[60],"form":[61],"limits":[62],"their":[63],"performance":[64,177],"transferability":[66,223],"since":[67],"PL":[68],"NL":[70],"syntax":[73,113],"rules":[74],"the":[76,99,111,123,134,138,144,150,158,162,168,175,179,198,210,222,227,236],"downstream":[77,95,185],"tasks":[78,96,200,212],"require":[79],"a":[80,87,129],"multimodal":[81],"representation.":[82,136],"Here":[83],"we":[84,220],"introduce":[85],"C3P,":[86],"Contrastive":[88],"Code-Comment":[89],"Pre-training":[90],"approach,":[91],"solve":[93],"various":[94],"pre-training":[98,237],"multi-representation":[100],"features":[101],"on":[102,183,197],"both":[103],"natural":[106,115],"syntax.":[107],"The":[108,188,239],"model":[109,243],"encodes":[110],"description":[117],"(comment)":[118],"two":[120],"encoders":[121,148],"encoded":[124],"embeddings":[125],"projected":[127],"into":[128],"multi-modal":[130],"space":[131],"learning":[133],"latent":[135,139],"In":[137],"space,":[140],"C3P":[141,193,225],"jointly":[142],"trains":[143],"comment":[147],"symmetric":[151],"loss":[152],"function,":[153],"which":[154,231],"aims":[155],"maximize":[157],"cosine":[159],"similarity":[160,169],"of":[161,170,178,201,213,224],"correct":[163],"code-comment":[164],"pairs":[165],"while":[166],"minimizing":[167],"unrelated":[171],"pairs.":[172],"We":[173],"verify":[174],"empirical":[176],"proposed":[180],"multiple":[184],"tasks.":[187],"comprehensive":[189],"experiments":[190],"demonstrate":[191],"that":[192],"outperforms":[194,255],"previous":[195],"work":[196],"understanding":[199],"search":[203],"clone,":[206],"generation":[211],"Furthermore,":[219],"validate":[221],"new":[228],"is":[232,260],"not":[233],"seen":[234],"in":[235,249],"stage.":[238],"results":[240],"show":[241],"our":[242],"surpasses":[244],"all":[245],"supervised":[246],"some":[250],"cases":[253],"even":[254],"prior":[256],"approaches.":[258],"Code":[259],"available":[261],"https://github.com/TerryPei/C3P.":[263]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2023-02-12T00:00:00"}