{"id":"https://openalex.org/W7126461371","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.125","title":"CODET: A Benchmark for Contrastive Dialectal Evaluation of Machine Translation","display_name":"CODET: A Benchmark for Contrastive Dialectal Evaluation of Machine Translation","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W7126461371","doi":"https://doi.org/10.18653/v1/2024.findings-eacl.125"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2024.findings-eacl.125","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.125","pdf_url":"https://aclanthology.org/2024.findings-eacl.125.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: EACL 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.findings-eacl.125.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061000138","display_name":"Mahfuz ibn Alam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Md Mahfuz Ibn Alam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101838570","display_name":"Sina Ahmadi","orcid":"https://orcid.org/0000-0001-7904-6551"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sina Ahmadi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124543162","display_name":"Antonios Anastasopoulos","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antonios Anastasopoulos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.57315101,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1790","last_page":"1859"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.8720999956130981,"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":0.8720999956130981,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.028599999845027924,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.010400000028312206,"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/machine-translation","display_name":"Machine translation","score":0.6265000104904175},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5364000201225281},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.38999998569488525},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2915000021457672},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.2822999954223633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6841999888420105},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6265000104904175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6026999950408936},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5656999945640564},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5364000201225281},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.38999998569488525},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.24570000171661377},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24490000307559967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.findings-eacl.125","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.125","pdf_url":"https://aclanthology.org/2024.findings-eacl.125.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: EACL 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-eacl.125","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-eacl.125","pdf_url":"https://aclanthology.org/2024.findings-eacl.125.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: EACL 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6923349499702454}],"awards":[{"id":"https://openalex.org/G1262899742","display_name":"Collaborative Research: RI: Small: NL(V)P: Natural Language (Variety) Processing","funder_award_id":"2125466","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4331521547","display_name":"Collaborative Research: Language Documentation with an Artificial Intelligence (AI) Helper","funder_award_id":"2109578","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6575747830","display_name":"Multitask Learning with Multilingual Resources for Better Natural Language Understanding","funder_award_id":"213976","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126461371.pdf","grobid_xml":"https://content.openalex.org/works/W7126461371.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Neural":[0],"machine":[1],"translation":[2],"(NMT)":[3],"systems":[4,57],"exhibit":[5],"limited":[6],"robustness":[7],"in":[8,23,92,152],"handling":[9],"source-side":[10],"linguistic":[11,145],"variations.Their":[12],"performance":[13],"tends":[14],"to":[15,38,42,54],"degrade":[16],"when":[17],"faced":[18],"with":[19],"even":[20],"slight":[21],"deviations":[22],"language":[24,129],"usage,":[25],"such":[26],"as":[27,46],"different":[28,77,81],"domains":[29],"or":[30,134],"variations":[31,45,78],"introduced":[32],"by":[33],"secondlanguage":[34],"speakers.It":[35],"is":[36,61,126,136],"intuitive":[37],"extend":[39],"this":[40,59,64,108],"observation":[41],"encompass":[43],"dialectal":[44,73,95],"well,":[47],"but":[48],"the":[49,52,86,97,113],"work":[50,159],"allowing":[51],"community":[53],"evaluate":[55],"MT":[56,89],"on":[58],"dimension":[60],"limited.To":[62],"alleviate":[63],"issue,":[65],"we":[66,110,158],"compile":[67],"and":[68,99,116,130],"release":[69],"CODET,":[70],"a":[71,128,132,137,143,148],"contrastive":[72],"benchmark":[74],"encompassing":[75],"891":[76],"from":[79],"twelve":[80],"languages.We":[82],"also":[83],"quantitatively":[84],"demonstrate":[85],"challenges":[87],"large":[88],"models":[90],"face":[91],"effectively":[93],"translating":[94],"variants.All":[96],"data":[98],"code":[100],"1":[101],"has":[102],"been":[103],"released.1":[104],"https://github.com/mahfuzibnalam/dialect_mt":[105],"2":[106],"In":[107],"paper,":[109],"will":[111],"use":[112],"terms":[114],"\"dialect\"":[115],"\"language":[117],"variety\"":[118],"interchangeably":[119],"for":[120,155],"readability":[121],"reasons.The":[122],"distinction":[123],"between":[124],"what":[125,131],"named":[127],"dialect":[133],"variety":[135],"complex":[138],"socioeconomic":[139],"phenomenon":[140],"rather":[141],"than":[142],"purely":[144],"one.We":[146],"add":[147],"bit":[149],"of":[150],"discussion":[151],"Section":[153],"3":[154],"each":[156],"variety/language":[157],"with.":[160]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-02T00:00:00"}