{"id":"https://openalex.org/W4403648112","doi":"https://doi.org/10.1145/3691621.3694939","title":"A Preliminary Study of Multilingual Code Language Models for Code Generation Task Using Translated Benchmarks","display_name":"A Preliminary Study of Multilingual Code Language Models for Code Generation Task Using Translated Benchmarks","publication_year":2024,"publication_date":"2024-10-22","ids":{"openalex":"https://openalex.org/W4403648112","doi":"https://doi.org/10.1145/3691621.3694939"},"language":"en","primary_location":{"id":"doi:10.1145/3691621.3694939","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3691621.3694939","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering Workshops","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.15470","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114361411","display_name":"Rohit Dandamudi","orcid":"https://orcid.org/0009-0009-5011-6507"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]},{"id":"https://openalex.org/I2800978909","display_name":"Kelowna General Hospital","ror":"https://ror.org/01j25h453","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I104778310","https://openalex.org/I2800978909"]},{"id":"https://openalex.org/I4405260628","display_name":"University of British Columbia, Okanagan Campus","ror":"https://ror.org/04241wz75","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490","https://openalex.org/I4405260628"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Rohit Dandamudi","raw_affiliation_strings":["University of British Columbia, Kelowna, Kelowna, Canada"],"raw_orcid":"https://orcid.org/0009-0009-5011-6507","affiliations":[{"raw_affiliation_string":"University of British Columbia, Kelowna, Kelowna, Canada","institution_ids":["https://openalex.org/I141945490","https://openalex.org/I2800978909","https://openalex.org/I4405260628"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077601628","display_name":"Gema Rodr\u00edguez-P\u00e9rez","orcid":"https://orcid.org/0000-0002-0062-8418"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]},{"id":"https://openalex.org/I2800978909","display_name":"Kelowna General Hospital","ror":"https://ror.org/01j25h453","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I104778310","https://openalex.org/I2800978909"]},{"id":"https://openalex.org/I4405260628","display_name":"University of British Columbia, Okanagan Campus","ror":"https://ror.org/04241wz75","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490","https://openalex.org/I4405260628"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Gema Rodriguez-Perez","raw_affiliation_strings":["University of British Columbia, Kelowna, Kelowna, Canada"],"raw_orcid":"https://orcid.org/0000-0002-0062-8418","affiliations":[{"raw_affiliation_string":"University of British Columbia, Kelowna, Kelowna, Canada","institution_ids":["https://openalex.org/I141945490","https://openalex.org/I2800978909","https://openalex.org/I4405260628"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7112,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.71533397,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"94","last_page":"99"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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":0.9991000294685364,"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/T12031","display_name":"Speech and dialogue systems","score":0.9955000281333923,"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/computer-science","display_name":"Computer science","score":0.8534034490585327},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6508487462997437},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6420038342475891},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.6350816488265991},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.6308879256248474},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42186835408210754},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.06912383437156677},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.05198383331298828}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8534034490585327},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6508487462997437},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6420038342475891},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6350816488265991},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.6308879256248474},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42186835408210754},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.06912383437156677},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05198383331298828},{"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/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3691621.3694939","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3691621.3694939","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering Workshops","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2411.15470","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.15470","pdf_url":"https://arxiv.org/pdf/2411.15470","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,"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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.15470","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.15470","pdf_url":"https://arxiv.org/pdf/2411.15470","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,"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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403648112.pdf","grobid_xml":"https://content.openalex.org/works/W4403648112.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2964315653","https://openalex.org/W4313547549","https://openalex.org/W4384345639","https://openalex.org/W4385562549","https://openalex.org/W4394769102","https://openalex.org/W4399631347","https://openalex.org/W4402665833"],"related_works":["https://openalex.org/W4231937131","https://openalex.org/W4389443772","https://openalex.org/W323219885","https://openalex.org/W2063928587","https://openalex.org/W1487966966","https://openalex.org/W1589342014","https://openalex.org/W2163672025","https://openalex.org/W2048831961","https://openalex.org/W1606349578","https://openalex.org/W4399567378"],"abstract_inverted_index":{"Evaluating":[0],"the":[1,29,39,43,53,91,111,119,128,142,154,164,168,176,182],"performance":[2,92,155,166],"of":[3,31,42,52,74,93,110,156],"Code":[4],"Language":[5],"Models":[6],"(CLMs)":[7],"for":[8,101,184],"software":[9],"engineering":[10],"tasks,":[11,56],"especially":[12],"in":[13,50,131,152,163,174],"multilingual":[14,98],"and":[15,38,121,171,197],"low-resource":[16],"programming":[17,36],"language":[18],"settings,":[19],"poses":[20],"significant":[21],"challenges.":[22],"These":[23,178],"challenges":[24,173],"are":[25,201,209],"primarily":[26],"due":[27],"to":[28,89,189,203],"lack":[30,73],"high-quality":[32],"benchmarks":[33,65,134,170],"across":[34,167],"various":[35],"languages":[37],"imbalanced":[40],"nature":[41],"CLMs":[44],"training":[45,143],"corpus.":[46],"Although":[47],"recent":[48],"advances":[49],"one":[51],"common":[54],"downstream":[55],"code":[57,102,113],"generation,":[58],"have":[59],"shown":[60],"promise":[61],"by":[62,118],"introducing":[63],"translated":[64,133,169,192],"using":[66],"different":[67],"methodologies,":[68],"there":[69],"is":[70],"a":[71,86,95],"current":[72],"empirical":[75,187],"evidence":[76],"assessing":[77],"these":[78,132],"benchmarks.":[79],"To":[80],"address":[81],"this":[82],"gap,":[83],"we":[84,159],"conducted":[85],"preliminary":[87],"study":[88],"evaluate":[90],"Poly-Coder,":[94],"pioneering":[96],"open-source,":[97],"CLM":[99],"built":[100],"generation.":[103],"We":[104],"utilized":[105],"two":[106],"existing":[107],"state-of-the-art":[108],"translations":[109],"popular":[112],"generation":[114],"benchmark,":[115],"HumanEval,":[116],"facilitated":[117],"OctoPack":[120],"MultiPL-E":[122],"studies.":[123],"Our":[124],"results":[125],"suggest":[126],"that":[127],"outcomes":[129],"observed":[130],"align":[135],"well":[136],"with":[137],"evaluation":[138],"metrics":[139],"used":[140],"during":[141],"phase,":[144],"such":[145],"as":[146],"perplexity,":[147],"thereby":[148],"validating":[149],"their":[150,205],"effectiveness":[151],"estimating":[153],"CLMs.":[157],"However,":[158],"identified":[160],"several":[161],"inconsistencies":[162],"CLMs'":[165],"encountered":[172],"replicating":[175],"results.":[177],"initial":[179],"insights":[180],"highlight":[181],"need":[183],"more":[185],"comprehensive":[186],"studies":[188,200],"fully":[190],"understand":[191],"benchmarks'":[193],"methodological":[194],"approaches,":[195],"limitations,":[196],"reproducibility.":[198],"Such":[199],"essential":[202],"ensure":[204],"reliability":[206],"before":[207],"they":[208],"widely":[210],"adopted.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2024-10-23T00:00:00"}
