{"id":"https://openalex.org/W4392163668","doi":"https://doi.org/10.3389/fdgth.2024.1211564","title":"Neural machine translation of clinical text: an empirical investigation into multilingual pre-trained language models and transfer-learning","display_name":"Neural machine translation of clinical text: an empirical investigation into multilingual pre-trained language models and transfer-learning","publication_year":2024,"publication_date":"2024-02-26","ids":{"openalex":"https://openalex.org/W4392163668","doi":"https://doi.org/10.3389/fdgth.2024.1211564","pmid":"https://pubmed.ncbi.nlm.nih.gov/38468693"},"language":"en","primary_location":{"id":"doi:10.3389/fdgth.2024.1211564","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdgth.2024.1211564","pdf_url":"https://www.frontiersin.org/journals/digital-health/articles/10.3389/fdgth.2024.1211564/pdf","source":{"id":"https://openalex.org/S4210170686","display_name":"Frontiers in Digital Health","issn_l":"2673-253X","issn":["2673-253X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Digital Health","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/journals/digital-health/articles/10.3389/fdgth.2024.1211564/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047560778","display_name":"Lifeng Han","orcid":"https://orcid.org/0000-0002-3221-2185"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Lifeng Han","raw_affiliation_strings":["Department of Computer Science, The University of Manchester, Manchester, United Kingom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Manchester, Manchester, United Kingom","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020735272","display_name":"Serge Gladkoff","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Serge Gladkoff","raw_affiliation_strings":["AI Lab, Logrus Global, Translation & Localization, Philadelphia, PA, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Lab, Logrus Global, Translation & Localization, Philadelphia, PA, United States","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043109148","display_name":"Gleb Erofeev","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gleb Erofeev","raw_affiliation_strings":["AI Lab, Logrus Global, Translation & Localization, Philadelphia, PA, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Lab, Logrus Global, Translation & Localization, Philadelphia, PA, United States","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073719890","display_name":"Irina Sorokina","orcid":"https://orcid.org/0000-0002-9404-3698"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Irina Sorokina","raw_affiliation_strings":["AI Lab, Logrus Global, Translation & Localization, Philadelphia, PA, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Lab, Logrus Global, Translation & Localization, Philadelphia, PA, United States","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093487462","display_name":"Betty Galiano","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Betty Galiano","raw_affiliation_strings":["Management Department, Ocean Translations, Rosario, Argentina"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Management Department, Ocean Translations, Rosario, Argentina","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005912060","display_name":"Goran Nenadi\u0107","orcid":"https://orcid.org/0000-0003-0795-5363"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Goran Nenadic","raw_affiliation_strings":["Department of Computer Science, The University of Manchester, Manchester, United Kingom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Manchester, Manchester, United Kingom","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5005912060","https://openalex.org/A5020735272","https://openalex.org/A5047560778"],"corresponding_institution_ids":["https://openalex.org/I28407311"],"apc_list":{"value":1900,"currency":"USD","value_usd":1900},"apc_paid":{"value":1900,"currency":"USD","value_usd":1900},"fwci":4.8066,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.95812502,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"6","issue":null,"first_page":"1211564","last_page":"1211564"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9994999766349792,"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/T10028","display_name":"Topic Modeling","score":0.991100013256073,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9700000286102295,"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":0.8081130385398865},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.7478910088539124},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7139277458190918},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6823375225067139},{"id":"https://openalex.org/keywords/terminology","display_name":"Terminology","score":0.5514175891876221},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.535633385181427},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.4642733931541443},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4301910698413849},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.42749032378196716},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38630732893943787},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08694738149642944}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8081130385398865},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7478910088539124},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7139277458190918},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6823375225067139},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.5514175891876221},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.535633385181427},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4642733931541443},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4301910698413849},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.42749032378196716},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38630732893943787},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08694738149642944},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3389/fdgth.2024.1211564","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdgth.2024.1211564","pdf_url":"https://www.frontiersin.org/journals/digital-health/articles/10.3389/fdgth.2024.1211564/pdf","source":{"id":"https://openalex.org/S4210170686","display_name":"Frontiers in Digital Health","issn_l":"2673-253X","issn":["2673-253X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Digital Health","raw_type":"journal-article"},{"id":"pmid:38468693","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38468693","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in digital health","raw_type":null},{"id":"pmh:oai:pure.atira.dk:openaire/fc41b183-c030-4994-902f-03778c8188c5","is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/publications/fc41b183-c030-4994-902f-03778c8188c5","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Han, L, Gladkoff, S, Erofeev, G, Sorokina, I, Galiano, B & Nenadic, G 2024, 'Neural machine translation of clinical text: an empirical investigation into multilingual pre-trained language models and transfer-learning', Frontiers in Digital Health, vol. 6, 1211564. https://doi.org/10.3389/fdgth.2024.1211564","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pubmedcentral.nih.gov:10926203","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10926203","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10926203/pdf/fdgth-06-1211564.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"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":"Front Digit Health","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:237b7c6532dc47d9a9fd5c6122a0fc03","is_oa":true,"landing_page_url":"https://doaj.org/article/237b7c6532dc47d9a9fd5c6122a0fc03","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Digital Health, Vol 6 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3389/fdgth.2024.1211564","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fdgth.2024.1211564","pdf_url":"https://www.frontiersin.org/journals/digital-health/articles/10.3389/fdgth.2024.1211564/pdf","source":{"id":"https://openalex.org/S4210170686","display_name":"Frontiers in Digital Health","issn_l":"2673-253X","issn":["2673-253X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Digital Health","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.699999988079071}],"awards":[{"id":"https://openalex.org/G1462525696","display_name":null,"funder_award_id":"EP/V047949/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G4423870334","display_name":null,"funder_award_id":"EP/V047949/1","funder_id":"https://openalex.org/F4320319997","funder_display_name":"Nuffield Foundation"}],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"},{"id":"https://openalex.org/F4320319997","display_name":"Nuffield Foundation","ror":"https://ror.org/0281jqk77"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4392163668.pdf"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W2095896451","https://openalex.org/W2095931818","https://openalex.org/W2111063183","https://openalex.org/W2130413976","https://openalex.org/W2159583324","https://openalex.org/W2404369708","https://openalex.org/W2884488303","https://openalex.org/W2979250794","https://openalex.org/W3013605954","https://openalex.org/W3044533399","https://openalex.org/W3093871477","https://openalex.org/W3107124456","https://openalex.org/W3128580531","https://openalex.org/W3131999495","https://openalex.org/W3135877859","https://openalex.org/W3144451117","https://openalex.org/W3164871893","https://openalex.org/W3165345393","https://openalex.org/W3194921886","https://openalex.org/W3211056521","https://openalex.org/W4210592931","https://openalex.org/W4214837599","https://openalex.org/W4226536126","https://openalex.org/W4229335055","https://openalex.org/W4385245566","https://openalex.org/W4389584441","https://openalex.org/W6674286886","https://openalex.org/W6713634263","https://openalex.org/W6739901393","https://openalex.org/W6784447870"],"related_works":["https://openalex.org/W2350593162","https://openalex.org/W2390350206","https://openalex.org/W1969477129","https://openalex.org/W2921208823","https://openalex.org/W2353483812","https://openalex.org/W2131808775","https://openalex.org/W2130038259","https://openalex.org/W2360756181","https://openalex.org/W2374093222","https://openalex.org/W2359533638"],"abstract_inverted_index":{"Clinical":[0],"text":[1,59,255],"and":[2,8,12,29,39,117,238,257],"documents":[3],"contain":[4],"very":[5,20],"rich":[6],"information":[7],"knowledge":[9,215,258],"in":[10,129,163,173,183,236],"healthcare,":[11],"their":[13],"processing":[14,33],"using":[15,68,89,187],"state-of-the-art":[16],"language":[17,36,80,99,149,157,195],"technology":[18],"becomes":[19],"important":[21],"for":[22,26,213,265],"building":[23],"intelligent":[24],"systems":[25],"supporting":[27],"healthcare":[28,239,254],"social":[30],"good.":[31],"This":[32],"includes":[34],"creating":[35],"understanding":[37],"models":[38,67,100,125,158],"translating":[40],"resources":[41],"into":[42,220],"other":[43,154],"natural":[44],"languages":[45],"to":[46,77,191,218,252],"share":[47],"domain-specific":[48,231],"cross-lingual":[49],"knowledge.":[50],"In":[51],"this":[52],"work,":[53],"we":[54,84],"conduct":[55],"investigations":[56],"on":[57,95,105,134,230,249],"clinical":[58,110,114,136,165,214,237],"machine":[60,232],"translation":[61,233],"by":[62,159],"examining":[63],"multilingual":[64,97],"neural":[65],"network":[66],"deep":[69],"learning":[70,92,179],"such":[71],"as":[72],"Transformer":[73],"based":[74,94,248],"structures.":[75],"Furthermore,":[76,139],"address":[78],"the":[79,130,146,153,164,174,177,188,203],"resource":[81],"imbalance":[82],"issue,":[83],"also":[85],"carry":[86],"out":[87,247],"experiments":[88],"a":[90,160,193],"transfer":[91,178],"methodology":[93],"massive":[96],"pre-trained":[98,148],"(MMPLMs).":[101],"The":[102],"experimental":[103,185],"results":[104],"three":[106],"sub-tasks":[107],"including":[108],"(1)":[109],"case":[111],"(CC),":[112],"(2)":[113],"terminology":[115],"(CT),":[116],"(3)":[118],"ontological":[119],"concept":[120],"(OC)":[121],"show":[122],"that":[123,145,198],"our":[124,140,184,250],"achieved":[126],"top-level":[127],"performances":[128],"ClinSpEn-2022":[131],"shared":[132],"task":[133],"English-Spanish":[135],"domain":[137,166],"data.":[138],"expert-based":[141],"human":[142],"evaluations":[143],"demonstrate":[144],"small-sized":[147],"model":[150,190],"(PLM)":[151],"outperformed":[152],"two":[155],"extra-large":[156],"large":[161],"margin":[162],"fine-tuning,":[167],"which":[168,209],"finding":[169],"was":[170,199],"never":[171],"reported":[172],"field.":[175],"Finally,":[176],"method":[180],"works":[181],"well":[182],"setting":[186],"WMT21fb":[189,207],"accommodate":[192],"new":[194],"space":[196],"Spanish":[197],"not":[200],"seen":[201],"at":[202],"pre-training":[204],"stage":[205],"within":[206],"itself,":[208],"deserves":[210],"more":[211,221],"exploitation":[212],"transformation,":[216],"e.g.":[217],"investigate":[219],"languages.":[222],"These":[223],"research":[224,242,266],"findings":[225],"can":[226,244],"shed":[227],"some":[228],"light":[229],"development,":[234],"especially":[235],"fields.":[240],"Further":[241],"projects":[243],"be":[245],"carried":[246],"work":[251],"improve":[253],"analytics":[256],"transformation.":[259],"Our":[260],"data":[261],"is":[262],"openly":[263],"available":[264],"purposes":[267],"at:":[268],"https://github.com/HECTA-UoM/ClinicalNMT.":[269]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":8}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}