{"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","doi":"https://doi.org/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":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2023.findings-emnlp.337.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030880662","display_name":"Weixiang Yan","orcid":null,"observed_orcids":[]},"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":false,"raw_author_name":"Weixiang Yan","raw_affiliation_strings":["University of California, Santa Barbara"],"raw_orcid":null,"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","observed_orcids":["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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yunzhe Li","orcid":null,"observed_orcids":[]},"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"],"raw_orcid":null,"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","observed_orcids":["https://orcid.org/0000-0003-0155-8009"]},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]},{"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"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN","KY","US"],"is_corresponding":false,"raw_author_name":"Qian Chen","raw_affiliation_strings":["Speech Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210086143","https://openalex.org/I4210095624","https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109801469","display_name":"Wen Wang","orcid":"https://orcid.org/0000-0002-9770-1115","observed_orcids":["https://orcid.org/0000-0002-9770-1115"]},"institutions":[{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]},{"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"]},{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN","KY","US"],"is_corresponding":false,"raw_author_name":"Wen Wang","raw_affiliation_strings":["Speech Lab, Alibaba Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Lab, Alibaba Group","institution_ids":["https://openalex.org/I4210086143","https://openalex.org/I4210095624","https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":19.1226,"has_fulltext":true,"cited_by_count":101,"citation_normalized_percentile":{"value":0.99560432,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"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":0.9984999895095825,"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":0.9984999895095825,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.000699999975040555,"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/T10028","display_name":"Topic Modeling","score":0.00019999999494757503,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/code-translation","display_name":"program translation","score":0.9959999918937683},{"id":"https://openalex.org/keywords/multilingual-programming-languages","display_name":"multilingual programming languages","score":0.7940000295639038},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8709999918937683},{"id":"https://openalex.org/keywords/low-resource-language-pairs","display_name":"low-resource language pairs","score":0.8050000071525574}],"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":3,"locations":[{"id":"doi:10.18653/v1/2023.findings-emnlp.337","doi":"https://doi.org/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":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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"},{"id":"pmh:oai:arXiv.org:2310.04951","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.04951","pdf_url":"https://arxiv.org/pdf/2310.04951","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2310.04951","doi":"https://doi.org/10.48550/arxiv.2310.04951","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.04951","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.findings-emnlp.337","doi":"https://doi.org/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":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389518960.pdf","grobid_xml":"https://content.openalex.org/works/W4389518960.grobid-xml"},"referenced_works_count":56,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2337363174","https://openalex.org/W2550821151","https://openalex.org/W2919290281","https://openalex.org/W2950599942","https://openalex.org/W2950621612","https://openalex.org/W2965373594","https://openalex.org/W3030163527","https://openalex.org/W3089307846","https://openalex.org/W3098605233","https://openalex.org/W3105038888","https://openalex.org/W3119507053","https://openalex.org/W3126675481","https://openalex.org/W3148399464","https://openalex.org/W3165784750","https://openalex.org/W3170092793","https://openalex.org/W3185341429","https://openalex.org/W3198685994","https://openalex.org/W3207298656","https://openalex.org/W3213368902","https://openalex.org/W4221015471","https://openalex.org/W4283210053","https://openalex.org/W4283799640","https://openalex.org/W4284664530","https://openalex.org/W4308731473","https://openalex.org/W4313563421","https://openalex.org/W4320167623","https://openalex.org/W4321524280","https://openalex.org/W4322718191","https://openalex.org/W4322760121","https://openalex.org/W4323059975","https://openalex.org/W4327487298","https://openalex.org/W4360584537","https://openalex.org/W4361807047","https://openalex.org/W4362679631","https://openalex.org/W4365205411","https://openalex.org/W4377121468","https://openalex.org/W4378510341","https://openalex.org/W4380993527","https://openalex.org/W4385571480","https://openalex.org/W4385571805","https://openalex.org/W4387428151","https://openalex.org/W4389519239","https://openalex.org/W4389519352","https://openalex.org/W4389524484","https://openalex.org/W4392240262","https://openalex.org/W4392669905","https://openalex.org/W4401042993","https://openalex.org/W4401043863","https://openalex.org/W4402516191","https://openalex.org/W6901758419","https://openalex.org/W7133210150","https://openalex.org/W7133222210","https://openalex.org/W7133224126","https://openalex.org/W7133231369","https://openalex.org/W7151510318"],"related_works":["https://openalex.org/W4409796840","https://openalex.org/W4394769102","https://openalex.org/W4416873814","https://openalex.org/W7213585243","https://openalex.org/W4411552547","https://openalex.org/W4385570080","https://openalex.org/W4405173210","https://openalex.org/W7202354304","https://openalex.org/W4400582609","https://openalex.org/W4403536514"],"abstract_inverted_index":{"Recent":[0],"code":[1,12,31,47,72,106,123,132,167,195,204],"translation":[2,7,32,48,133,142,196],"techniques":[3],"exploit":[4],"neural":[5],"machine":[6],"models":[8,110],"to":[9,17,19,24],"translate":[10],"source":[11],"from":[13],"one":[14],"programming":[15,42,69,87,94],"language":[16,109,149],"another":[18],"satisfy":[20],"production":[21],"compatibility":[22],"or":[23],"improve":[25],"efficiency":[26],"of":[27,40,53,68,75,104,144,194],"codebase":[28],"maintenance.Most":[29],"existing":[30],"datasets":[33,178,202],"only":[34],"focus":[35],"on":[36,46,176],"a":[37,59,114,158],"single":[38],"pair":[39],"popular":[41,86,97],"languages.To":[43],"advance":[44],"research":[45],"and":[49,96,99,134,147,151,179,191,203],"meet":[50],"diverse":[51],"requirements":[52],"real-world":[54],"applications,":[55],"we":[56,172],"construct":[57],"CodeTransOcean,":[58],"large-scale":[60],"comprehensive":[61],"benchmark":[62],"that":[63],"supports":[64],"the":[65,141,153],"largest":[66],"variety":[67],"languages":[70,95],"for":[71,90,101,119,131,165,183,189,197],"translation.CodeTransOcean":[73],"consists":[74],"three":[76],"novel":[77,115,159],"multilingual":[78,128],"datasets,":[79],"namely,":[80],"MultilingualTrans":[81],"supporting":[82],"translations":[83],"between":[84,92],"multiple":[85],"languages,":[88],"NicheTrans":[89],"translating":[91,120],"niche":[93],"ones,":[98],"LLMTrans":[100],"evaluating":[102],"executability":[103],"translated":[105],"by":[107],"large":[108],"(LLMs).CodeTransOcean":[111],"also":[112,156],"includes":[113],"cross-framework":[116],"dataset,":[117],"DLTrans,":[118],"deep":[121],"learning":[122],"across":[124],"different":[125],"frameworks.We":[126],"develop":[127],"modeling":[129],"approaches":[130],"demonstrate":[135],"their":[136],"great":[137],"potential":[138,182],"in":[139],"improving":[140],"quality":[143],"both":[145],"low-resource":[146],"high-resource":[148],"pairs":[150],"boosting":[152],"training":[154],"efficiency.We":[155],"propose":[157],"evaluation":[160],"metric":[161],"Debugging":[162],"Success":[163],"Rate@K":[164],"program-level":[166],"translation.Last":[168],"but":[169],"not":[170],"least,":[171],"evaluate":[173],"LLM":[174],"ChatGPT":[175],"our":[177],"investigate":[180],"its":[181],"fuzzy":[184],"execution":[185],"predictions.We":[186],"build":[187],"baselines":[188],"CodeTransOcean":[190,201],"analyze":[192],"challenges":[193],"guiding":[198],"future":[199],"research.The":[200],"are":[205],"publicly":[206],"available":[207],"at":[208],"https://github.":[209],"com/WeixiangYAN/CodeTransOcean.":[210]},"counts_by_year":[{"year":2026,"cited_by_count":49},{"year":2025,"cited_by_count":43},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2023-12-10T00:00:00"}