{"id":"https://openalex.org/W4416033635","doi":"https://doi.org/10.18653/v1/2025.wmt-1.8","title":"OpenWHO: A Document-Level Parallel Corpus for Health Translation in Low-Resource Languages","display_name":"OpenWHO: A Document-Level Parallel Corpus for Health Translation in Low-Resource Languages","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416033635","doi":"https://doi.org/10.18653/v1/2025.wmt-1.8"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.wmt-1.8","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.wmt-1.8","pdf_url":"https://aclanthology.org/2025.wmt-1.8.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 Tenth Conference on Machine Translation","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.wmt-1.8.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5095762190","display_name":"Rapha\u00ebl Merx","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Raphael Merx","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059778915","display_name":"Hanna Suominen","orcid":"https://orcid.org/0000-0002-4195-1641"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hanna Suominen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078530959","display_name":"Trevor Cohn","orcid":"https://orcid.org/0000-0003-4363-1673"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Trevor Cohn","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5055467011","display_name":"Ekaterina Vylomova","orcid":"https://orcid.org/0000-0002-4058-5459"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ekaterina Vylomova","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6768,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86933347,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"142","last_page":"160"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.690500020980835,"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":0.690500020980835,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.061900001019239426,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.02590000070631504,"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/translation","display_name":"Translation (biology)","score":0.5546000003814697},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.38609999418258667},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.29750001430511475},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2924000024795532},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.23839999735355377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6518999934196472},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5687000155448914},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5546000003814697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.503600001335144},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.48410001397132874},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.38609999418258667},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.23839999735355377},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2303999960422516}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.wmt-1.8","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.wmt-1.8","pdf_url":"https://aclanthology.org/2025.wmt-1.8.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 Tenth Conference on Machine Translation","raw_type":"proceedings-article"},{"id":"pmh:oai:openresearch-repository.anu.edu.au:1885/733807686","is_oa":false,"landing_page_url":"https://hdl.handle.net/1885/733807686","pdf_url":null,"source":{"id":"https://openalex.org/S4306402539","display_name":"ANU Open Research (Australian National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I118347636","host_organization_name":"Australian National University","host_organization_lineage":["https://openalex.org/I118347636"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.wmt-1.8","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.wmt-1.8","pdf_url":"https://aclanthology.org/2025.wmt-1.8.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 Tenth Conference on Machine Translation","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307856","display_name":"World Health Organization","ror":"https://ror.org/01f80g185"},{"id":"https://openalex.org/F4320320974","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416033635.pdf","grobid_xml":"https://content.openalex.org/works/W4416033635.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"machine":[1],"translation":[2,129],"(MT),":[3],"health":[4,151],"is":[5,17],"a":[6,18,36,63,103],"highstakes":[7],"domain":[8],"characterised":[9],"by":[10],"widespread":[11],"deployment":[12],"and":[13,43],"domain-specific":[14],"vocabulary.However,":[15],"there":[16],"lack":[19],"of":[20,40,66,70,127],"MT":[21,87,96,148],"evaluation":[22],"datasets":[23],"for":[24],"low-resource":[25,112,147],"languages":[26],"in":[27,133,149],"this":[28,31,75],"domain.To":[29],"address":[30],"gap,":[32],"we":[33,78,115],"introduce":[34],"OpenWHO,":[35],"document-level":[37,128],"parallel":[38],"corpus":[39,141],"2,978":[41],"documents":[42],"26,824":[44],"sentences":[45],"from":[46,53,59],"the":[47,125,139,150],"World":[48],"Health":[49],"Organization's":[50],"e-learning":[51],"platform.Sourced":[52],"expert-authored,":[54],"professionally":[55],"translated":[56],"materials":[57],"shielded":[58],"web-crawling,":[60],"OpenWHO":[61,140],"spans":[62],"diverse":[64],"range":[65],"over":[67,108],"20":[68],"languages,":[69],"which":[71],"nine":[72],"are":[73,130],"low-resource.Leveraging":[74],"new":[76],"resource,":[77],"evaluate":[79],"modern":[80],"large":[81],"language":[82],"models":[83],"(LLMs)":[84],"against":[85],"traditional":[86,95],"models.Our":[88],"findings":[89],"reveal":[90],"that":[91,124],"LLMs":[92],"consistently":[93],"outperform":[94],"models,":[97],"with":[98],"Gemini":[99],"2.5":[100],"Flash":[101],"achieving":[102],"+4.79":[104],"ChrF":[105],"point":[106],"improvement":[107],"NLLB-54B":[109],"on":[110],"our":[111],"test":[113],"set.Further,":[114],"investigate":[116],"how":[117],"LLM":[118],"context":[119],"utilisation":[120],"affects":[121],"accuracy,":[122],"finding":[123],"benefits":[126],"most":[131],"pronounced":[132],"specialised":[134],"domains":[135],"like":[136],"health.We":[137],"release":[138],"to":[142],"encourage":[143],"further":[144],"research":[145],"into":[146],"domain.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-08T00:00:00"}