{"id":"https://openalex.org/W4416036091","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1018","title":"Languages Still Left Behind: Toward a Better Multilingual Machine Translation Benchmark","display_name":"Languages Still Left Behind: Toward a Better Multilingual Machine Translation Benchmark","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416036091","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1018"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1018","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1018","pdf_url":"https://aclanthology.org/2025.emnlp-main.1018.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.1018.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002100389","display_name":"Chihiro Taguchi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chihiro Taguchi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023873669","display_name":"Sabine Mai","orcid":"https://orcid.org/0000-0002-5797-2201"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seng Mai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086489672","display_name":"Keita Kurabe","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keita Kurabe","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042174785","display_name":"Yusuke Sakai","orcid":"https://orcid.org/0000-0001-8810-4813"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yusuke Sakai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119710190","display_name":"Georgina Agyei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Georgina Agyei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037555476","display_name":"S. M. Ali Eslami","orcid":"https://orcid.org/0000-0003-1838-5589"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Soudabeh Eslami","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5036026526","display_name":"David Chiang","orcid":"https://orcid.org/0000-0002-0435-4864"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Chiang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5002100389"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17479976,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20142","last_page":"20154"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.6854000091552734,"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":0.6854000091552734,"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/T10759","display_name":"Translation Studies and Practices","score":0.01759999990463257,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T14347","display_name":"Big Data and Digital Economy","score":0.01759999990463257,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6542999744415283},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.3950999975204468},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.38420000672340393},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3172000050544739}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6985999941825867},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6542999744415283},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5706999897956848},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5489000082015991},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3950999975204468},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.38420000672340393},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3361999988555908},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2614000141620636}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.1018","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1018","pdf_url":"https://aclanthology.org/2025.emnlp-main.1018.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1018","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1018","pdf_url":"https://aclanthology.org/2025.emnlp-main.1018.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":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1319247439","display_name":"RI: Small: Learning to Retrieve Structured Information for Summarization and Translation  of Unstructured Text","funder_award_id":"2137396","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2154942263","display_name":"\u30b8\u30f3\u30dd\u30fc\u8a9e\u53e3\u627f\u8cc7\u6599\u306e\u8cc7\u6e90\u5316\u306b\u95a2\u3059\u308b\u7814\u7a76","funder_award_id":"24K03887","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G2661759313","display_name":"Collaborative Research: Language Documentation with an Artificial Intelligence (AI) Helper","funder_award_id":"2109709","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7752643416","display_name":null,"funder_award_id":"Japan","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8582348533","display_name":"\u7279\u6b8a\u5b97\u6559\u96c6\u56e3\u5bb6\u65cf\u306e\u6cd5\u793e\u4f1a\u5b66\u7684\u7814\u7a76","funder_award_id":"21097","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416036091.pdf","grobid_xml":"https://content.openalex.org/works/W4416036091.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multilingual":[0],"machine":[1],"translation":[2,26,165],"(MT)":[3],"benchmarks":[4,145],"play":[5],"a":[6],"central":[7],"role":[8],"in":[9,41,55,110,159],"evaluating":[10],"the":[11,18,56,70,76,90,111],"capabilities":[12],"of":[13],"modern":[14],"MT":[15,117,144],"systems.Among":[16],"them,":[17],"FLORES+":[19,127],"benchmark":[20],"is":[21],"widely":[22],"used,":[23],"offering":[24],"English-to-many":[25],"data":[27,40,123],"for":[28,59,142],"over":[29],"200":[30],"languages,":[31],"curated":[32],"with":[33],"strict":[34],"quality":[35,73],"control":[36],"protocols.However,":[37],"we":[38,114,140],"study":[39],"four":[42],"languages":[43],"(Asante":[44],"Twi,":[45],"Japanese,":[46],"Jinghpaw,":[47],"and":[48,51,75,86,149],"South":[49],"Azerbaijani)":[50],"uncover":[52],"critical":[53],"shortcomings":[54],"benchmark's":[57],"suitability":[58],"truly":[60],"multilingual":[61,143],"evaluation.Human":[62],"assessments":[63],"reveal":[64],"that":[65,79,95,116,146],"many":[66],"translations":[67],"fall":[68],"below":[69],"claimed":[71],"90%":[72],"standard,":[74],"annotators":[77],"report":[78],"source":[80,152],"sentences":[81],"are":[82],"often":[83],"too":[84],"domain-specific":[85],"culturally":[87,150],"biased":[88],"toward":[89],"English-speaking":[91],"world.We":[92],"further":[93],"demonstrate":[94],"simple":[96],"heuristics,":[97],"such":[98],"as":[99],"copying":[100],"named":[101,157],"entities,":[102,158],"can":[103],"yield":[104],"non-trivial":[105],"BLEU":[106],"scores,":[107],"suggesting":[108],"vulnerabilities":[109],"evaluation":[112,135],"protocol.Notably,":[113],"show":[115],"models":[118],"trained":[119],"on":[120,126,132,137,156],"high-quality,":[121],"naturalistic":[122],"perform":[124],"poorly":[125],"while":[128],"achieving":[129],"significant":[130],"gains":[131],"our":[133],"domain-relevant":[134],"set.Based":[136],"these":[138],"findings,":[139],"advocate":[141],"use":[147],"domain-general":[148],"neutral":[151],"texts":[153],"rely":[154],"less":[155],"order":[160],"to":[161],"better":[162],"reflect":[163],"real-world":[164],"challenges.":[166]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-11-08T00:00:00"}