{"id":"https:\/\/openalex.org\/W4389518960","doi":"https:\/\/doi.org\/10.18653\/v1\/2023.findings-emnlp.337","title":"CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translation","display_name":"CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translation","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https:\/\/openalex.org\/W4389518960","doi":"https:\/\/doi.org\/10.18653\/v1\/2023.findings-emnlp.337"},"language":"en","primary_location":{"id":"doi:10.18653\/v1\/2023.findings-emnlp.337","is_oa":true,"landing_page_url":"https:\/\/doi.org\/10.18653\/v1\/2023.findings-emnlp.337","pdf_url":"https:\/\/aclanthology.org\/2023.findings-emnlp.337.pdf","source":null,"license":"cc-by","license_id":"https:\/\/openalex.org\/licenses\/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https:\/\/aclanthology.org\/2023.findings-emnlp.337.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https:\/\/openalex.org\/A5030880662","display_name":"Weixiang Yan","orcid":null},"institutions":[{"id":"https:\/\/openalex.org\/I154570441","display_name":"University of California, Santa Barbara","ror":"https:\/\/ror.org\/02t274463","country_code":"US","type":"education","lineage":["https:\/\/openalex.org\/I154570441"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Weixiang Yan","raw_affiliation_strings":["University of California, Santa Barbara"],"affiliations":[{"raw_affiliation_string":"University of California, Santa Barbara","institution_ids":["https:\/\/openalex.org\/I154570441"]}]},{"author_position":"middle","author":{"id":"https:\/\/openalex.org\/A5101210809","display_name":"Yuchen Tian","orcid":"https:\/\/orcid.org\/0009-0002-4952-721X"},"institutions":[{"id":"https:\/\/openalex.org\/I889458895","display_name":"University of Hong Kong","ror":"https:\/\/ror.org\/02zhqgq86","country_code":"HK","type":"education","lineage":["https:\/\/openalex.org\/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yuchen Tian","raw_affiliation_strings":["The University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https:\/\/openalex.org\/I889458895"]}]},{"author_position":"middle","author":{"id":"https:\/\/openalex.org\/A5076083959","display_name":"Yunzhe Li","orcid":"https:\/\/orcid.org\/0000-0002-9129-8871"},"institutions":[{"id":"https:\/\/openalex.org\/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https:\/\/ror.org\/047426m28","country_code":"US","type":"education","lineage":["https:\/\/openalex.org\/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunzhe Li","raw_affiliation_strings":["University of Illinois at Urbana-Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https:\/\/openalex.org\/I157725225"]}]},{"author_position":"middle","author":{"id":"https:\/\/openalex.org\/A5100428495","display_name":"Qian Chen","orcid":"https:\/\/orcid.org\/0000-0003-0155-8009"},"institutions":[{"id":"https:\/\/openalex.org\/I4210095624","display_name":"Alibaba Group (United States)","ror":"https:\/\/ror.org\/00rn0m335","country_code":"US","type":"company","lineage":["https:\/\/openalex.org\/I4210095624","https:\/\/openalex.org\/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qian Chen","raw_affiliation_strings":["Speech Lab, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Speech Lab, Alibaba Group","institution_ids":["https:\/\/openalex.org\/I4210095624"]}]},{"author_position":"last","author":{"id":"https:\/\/openalex.org\/A5109801469","display_name":"Wen Wang","orcid":"https:\/\/orcid.org\/0000-0002-9770-1115"},"institutions":[{"id":"https:\/\/openalex.org\/I4210095624","display_name":"Alibaba Group (United States)","ror":"https:\/\/ror.org\/00rn0m335","country_code":"US","type":"company","lineage":["https:\/\/openalex.org\/I4210095624","https:\/\/openalex.org\/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen Wang","raw_affiliation_strings":["Speech Lab, Alibaba Group"],"affiliations":[{"raw_affiliation_string":"Speech Lab, Alibaba Group","institution_ids":["https:\/\/openalex.org\/I4210095624"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https:\/\/openalex.org\/A5030880662"],"corresponding_institution_ids":["https:\/\/openalex.org\/I154570441"],"apc_list":null,"apc_paid":null,"fwci":9.0135,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.97880728,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5067","last_page":"5089"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https:\/\/openalex.org\/T10260","display_name":"Software Engineering Research","score":0.9681000113487244,"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":0.9681000113487244,"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\/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9571999907493591,"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\/T10036","display_name":"Advanced Neural Network Applications","score":0.9409999847412109,"subfield":{"id":"https:\/\/openalex.org\/subfields\/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8748153448104858},{"id":"https:\/\/openalex.org\/keywords\/machine-translation","display_name":"Machine translation","score":0.6508039236068726},{"id":"https:\/\/openalex.org\/keywords\/codebase","display_name":"Codebase","score":0.5750518441200256},{"id":"https:\/\/openalex.org\/keywords\/artificial-intelligence","display_name":"Artificial intelligence","score":0.5283043384552002},{"id":"https:\/\/openalex.org\/keywords\/debugging","display_name":"Debugging","score":0.46800485253334045},{"id":"https:\/\/openalex.org\/keywords\/programming-language","display_name":"Programming language","score":0.4504448473453522},{"id":"https:\/\/openalex.org\/keywords\/natural-language-processing","display_name":"Natural language processing","score":0.40493687987327576},{"id":"https:\/\/openalex.org\/keywords\/source-code","display_name":"Source code","score":0.3862444758415222},{"id":"https:\/\/openalex.org\/keywords\/machine-learning","display_name":"Machine learning","score":0.34848034381866455}],"concepts":[{"id":"https:\/\/openalex.org\/C41008148","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q21198","display_name":"Computer science","level":0,"score":0.8748153448104858},{"id":"https:\/\/openalex.org\/C203005215","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q79798","display_name":"Machine translation","level":2,"score":0.6508039236068726},{"id":"https:\/\/openalex.org\/C51929080","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q2425187","display_name":"Codebase","level":3,"score":0.5750518441200256},{"id":"https:\/\/openalex.org\/C154945302","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5283043384552002},{"id":"https:\/\/openalex.org\/C168065819","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q845566","display_name":"Debugging","level":2,"score":0.46800485253334045},{"id":"https:\/\/openalex.org\/C199360897","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q9143","display_name":"Programming language","level":1,"score":0.4504448473453522},{"id":"https:\/\/openalex.org\/C204321447","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q30642","display_name":"Natural language processing","level":1,"score":0.40493687987327576},{"id":"https:\/\/openalex.org\/C43126263","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q128751","display_name":"Source code","level":2,"score":0.3862444758415222},{"id":"https:\/\/openalex.org\/C119857082","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q2539","display_name":"Machine learning","level":1,"score":0.34848034381866455}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653\/v1\/2023.findings-emnlp.337","is_oa":true,"landing_page_url":"https:\/\/doi.org\/10.18653\/v1\/2023.findings-emnlp.337","pdf_url":"https:\/\/aclanthology.org\/2023.findings-emnlp.337.pdf","source":null,"license":"cc-by","license_id":"https:\/\/openalex.org\/licenses\/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2023","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653\/v1\/2023.findings-emnlp.337","is_oa":true,"landing_page_url":"https:\/\/doi.org\/10.18653\/v1\/2023.findings-emnlp.337","pdf_url":"https:\/\/aclanthology.org\/2023.findings-emnlp.337.pdf","source":null,"license":"cc-by","license_id":"https:\/\/openalex.org\/licenses\/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https:\/\/metadata.un.org\/sdg\/4","score":0.6399999856948853,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https:\/\/content.openalex.org\/works\/W4389518960.pdf"},"referenced_works_count":56,"referenced_works":["https:\/\/openalex.org\/W2101105183","https:\/\/openalex.org\/W2550821151","https:\/\/openalex.org\/W2919290281","https:\/\/openalex.org\/W2963088995","https:\/\/openalex.org\/W2965373594","https:\/\/openalex.org\/W2970575144","https:\/\/openalex.org\/W3089307846","https:\/\/openalex.org\/W3098044990","https:\/\/openalex.org\/W3098605233","https:\/\/openalex.org\/W3104907093","https:\/\/openalex.org\/W3105038888","https:\/\/openalex.org\/W3119507053","https:\/\/openalex.org\/W3126675481","https:\/\/openalex.org\/W3154248444","https:\/\/openalex.org\/W3161457214","https:\/\/openalex.org\/W3165784750","https:\/\/openalex.org\/W3170092793","https:\/\/openalex.org\/W3185341429","https:\/\/openalex.org\/W3198685994","https:\/\/openalex.org\/W4221015471","https:\/\/openalex.org\/W4221143046","https:\/\/openalex.org\/W4281557260","https:\/\/openalex.org\/W4283210053","https:\/\/openalex.org\/W4283706798","https:\/\/openalex.org\/W4283799640","https:\/\/openalex.org\/W4284664530","https:\/\/openalex.org\/W4286904762","https:\/\/openalex.org\/W4292779060","https:\/\/openalex.org\/W4308731473","https:\/\/openalex.org\/W4313563421","https:\/\/openalex.org\/W4317940234","https:\/\/openalex.org\/W4319793767","https:\/\/openalex.org\/W4320167623","https:\/\/openalex.org\/W4320830156","https:\/\/openalex.org\/W4321524280","https:\/\/openalex.org\/W4322718191","https:\/\/openalex.org\/W4322760121","https:\/\/openalex.org\/W4323059975","https:\/\/openalex.org\/W4323651265","https:\/\/openalex.org\/W4327487298","https:\/\/openalex.org\/W4353112996","https:\/\/openalex.org\/W4361188984","https:\/\/openalex.org\/W4361807047","https:\/\/openalex.org\/W4361866080","https:\/\/openalex.org\/W4362598574","https:\/\/openalex.org\/W4362679631","https:\/\/openalex.org\/W4364387438","https:\/\/openalex.org\/W4365205411","https:\/\/openalex.org\/W4367365458","https:\/\/openalex.org\/W4376652621","https:\/\/openalex.org\/W4377121468","https:\/\/openalex.org\/W4377987838","https:\/\/openalex.org\/W4378510341","https:\/\/openalex.org\/W4380993527","https:\/\/openalex.org\/W4385571480","https:\/\/openalex.org\/W4387428151"],"related_works":["https:\/\/openalex.org\/W2061417947","https:\/\/openalex.org\/W2344367508","https:\/\/openalex.org\/W2571988079","https:\/\/openalex.org\/W4291746025","https:\/\/openalex.org\/W2098629748","https:\/\/openalex.org\/W2147884840","https:\/\/openalex.org\/W4244608052","https:\/\/openalex.org\/W2144528247","https:\/\/openalex.org\/W4312050194","https:\/\/openalex.org\/W3188088379"],"abstract_inverted_index":{"Recent":[0],"code":[1,12,32,49,74,109,127,137,173,203,213],"translation":[2,7,33,50,138,147,204],"techniques":[3],"exploit":[4],"neural":[5],"machine":[6],"models":[8,113],"to":[9,17,19,24],"translate":[10],"source":[11],"from":[13],"one":[14],"programming":[15,43,71,90,97],"language":[16,112,154],"another":[18],"satisfy":[20],"production":[21],"compatibility":[22],"or":[23],"improve":[25],"efficiency":[26],"of":[27,41,55,70,78,107,149,202],"codebase":[28],"maintenance.":[29],"Most":[30],"existing":[31],"datasets":[34,185,211],"only":[35],"focus":[36],"on":[37,48,183],"a":[38,61,118,164],"single":[39],"pair":[40],"popular":[42,89,100],"languages.":[44],"To":[45],"advance":[46],"research":[47],"and":[51,99,102,139,152,156,186,199,212],"meet":[52],"diverse":[53],"requirements":[54],"real-world":[56],"applications,":[57],"we":[58,179],"construct":[59],"**CodeTransOcean**,":[60],"large-scale":[62],"comprehensive":[63],"benchmark":[64],"that":[65],"supports":[66],"the":[67,146,158],"largest":[68],"variety":[69],"languages":[72,98],"for":[73,93,104,123,136,171,190,197,205],"translation.":[75,174],"CodeTransOcean":[76,115,198,210],"consists":[77],"three":[79],"novel":[80,119,165],"multilingual":[81,133],"datasets,":[82],"namely,":[83],"**MultilingualTrans**":[84],"supporting":[85],"translations":[86],"between":[87,95],"multiple":[88],"languages,":[91],"**NicheTrans**":[92],"translating":[94,124],"niche":[96],"ones,":[101],"**LLMTrans**":[103],"evaluating":[105],"executability":[106],"translated":[108],"by":[110],"large":[111],"(LLMs).":[114],"also":[116,162],"includes":[117],"cross-framework":[120],"dataset,":[121],"**DLTrans**,":[122],"deep":[125],"learning":[126],"across":[128],"different":[129],"frameworks.":[130],"We":[131,161,194],"develop":[132],"modeling":[134],"approaches":[135],"demonstrate":[140],"their":[141],"great":[142],"potential":[143,189],"in":[144],"improving":[145],"quality":[148],"both":[150],"low-resource":[151],"high-resource":[153],"pairs":[155],"boosting":[157],"training":[159],"efficiency.":[160],"propose":[163],"evaluation":[166],"metric":[167],"**Debugging":[168],"Success":[169],"Rate@K**":[170],"program-level":[172],"Last":[175],"but":[176],"not":[177],"least,":[178],"evaluate":[180],"LLM":[181],"ChatGPT":[182],"our":[184],"investigate":[187],"its":[188],"fuzzy":[191],"execution":[192],"predictions.":[193],"build":[195],"baselines":[196],"analyze":[200],"challenges":[201],"guiding":[206],"future":[207],"research.":[208],"The":[209],"are":[214],"publicly":[215],"available":[216],"at":[217],"https:\/\/github.com\/WeixiangYAN\/CodeTransOcean.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}