{"id":"https://openalex.org/W3198156935","doi":"https://doi.org/10.1186/s12911-021-01621-8","title":"ParaMed: a parallel corpus for English\u2013Chinese translation in the biomedical domain","display_name":"ParaMed: a parallel corpus for English\u2013Chinese translation in the biomedical domain","publication_year":2021,"publication_date":"2021-09-06","ids":{"openalex":"https://openalex.org/W3198156935","doi":"https://doi.org/10.1186/s12911-021-01621-8","mag":"3198156935","pmid":"https://pubmed.ncbi.nlm.nih.gov/34488734"},"language":"en","primary_location":{"id":"doi:10.1186/s12911-021-01621-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12911-021-01621-8","pdf_url":"https://bmcmedinformdecismak.biomedcentral.com/track/pdf/10.1186/s12911-021-01621-8","source":{"id":"https://openalex.org/S107516304","display_name":"BMC Medical Informatics and Decision Making","issn_l":"1472-6947","issn":["1472-6947"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Medical Informatics and Decision Making","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcmedinformdecismak.biomedcentral.com/track/pdf/10.1186/s12911-021-01621-8","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052636953","display_name":"Boxiang Liu","orcid":"https://orcid.org/0000-0002-2595-4463"},"institutions":[{"id":"https://openalex.org/I4210119130","display_name":"Institute for Learning Innovation","ror":"https://ror.org/02krjt890","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210119130"]},{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN","US"],"is_corresponding":true,"raw_author_name":"Boxiang Liu","raw_affiliation_strings":["Institute of Deep Learning, Baidu Research, Sunnyvale, USA. jollier.liu@gmail.com","Institute of Deep Learning, Baidu Research, Sunnyvale, USA"],"raw_orcid":"https://orcid.org/0000-0002-2595-4463","affiliations":[{"raw_affiliation_string":"Institute of Deep Learning, Baidu Research, Sunnyvale, USA. jollier.liu@gmail.com","institution_ids":["https://openalex.org/I98301712"]},{"raw_affiliation_string":"Institute of Deep Learning, Baidu Research, Sunnyvale, USA","institution_ids":["https://openalex.org/I4210119130"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006404928","display_name":"Liang Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]},{"id":"https://openalex.org/I4210119130","display_name":"Institute for Learning Innovation","ror":"https://ror.org/02krjt890","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210119130"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liang Huang","raw_affiliation_strings":["Institute of Deep Learning, Baidu Research, Sunnyvale, USA","School of Electrical Engineering and Computer Science, Oregon State University, Corvallis, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Deep Learning, Baidu Research, Sunnyvale, USA","institution_ids":["https://openalex.org/I4210119130"]},{"raw_affiliation_string":"School of Electrical Engineering and Computer Science, Oregon State University, Corvallis, USA","institution_ids":["https://openalex.org/I131249849"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5052636953"],"corresponding_institution_ids":["https://openalex.org/I4210119130","https://openalex.org/I98301712"],"apc_list":{"value":1570,"currency":"GBP","value_usd":1925},"apc_paid":{"value":1570,"currency":"GBP","value_usd":1925},"fwci":1.959,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.88740546,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"21","issue":"1","first_page":"258","last_page":"258"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.5946999788284302,"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":0.5946999788284302,"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":0.1054999977350235,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.06390000134706497,"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/health-informatics","display_name":"Health informatics","score":0.7617611289024353},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.669391393661499},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.657417893409729},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5635259747505188},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.552678108215332},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.48125120997428894},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"Parallel corpora","score":0.42647647857666016},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4009397029876709},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.2202979028224945},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.10461339354515076},{"id":"https://openalex.org/keywords/public-health","display_name":"Public health","score":0.10096439719200134},{"id":"https://openalex.org/keywords/pathology","display_name":"Pathology","score":0.09554934501647949},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06486234068870544}],"concepts":[{"id":"https://openalex.org/C145642194","wikidata":"https://www.wikidata.org/wiki/Q870895","display_name":"Health informatics","level":3,"score":0.7617611289024353},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.669391393661499},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.657417893409729},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5635259747505188},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.552678108215332},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.48125120997428894},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.42647647857666016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4009397029876709},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.2202979028224945},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.10461339354515076},{"id":"https://openalex.org/C138816342","wikidata":"https://www.wikidata.org/wiki/Q189603","display_name":"Public health","level":2,"score":0.10096439719200134},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.09554934501647949},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06486234068870544},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[{"descriptor_ui":"D002681","descriptor_name":"China","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002681","descriptor_name":"China","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002681","descriptor_name":"China","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002681","descriptor_name":"China","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014175","descriptor_name":"Translating","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014175","descriptor_name":"Translating","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014175","descriptor_name":"Translating","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014175","descriptor_name":"Translating","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12911-021-01621-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12911-021-01621-8","pdf_url":"https://bmcmedinformdecismak.biomedcentral.com/track/pdf/10.1186/s12911-021-01621-8","source":{"id":"https://openalex.org/S107516304","display_name":"BMC Medical Informatics and Decision Making","issn_l":"1472-6947","issn":["1472-6947"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Medical Informatics and Decision Making","raw_type":"journal-article"},{"id":"pmid:34488734","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34488734","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":"BMC medical informatics and decision making","raw_type":null},{"id":"pmh:oai:doaj.org/article:ea72f7a4d387413d988d9c3bbe1a9133","is_oa":true,"landing_page_url":"https://doaj.org/article/ea72f7a4d387413d988d9c3bbe1a9133","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":"BMC Medical Informatics and Decision Making, Vol 21, Iss 1, Pp 1-11 (2021)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:8422666","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8422666","pdf_url":null,"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":"BMC Med Inform Decis Mak","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12911-021-01621-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12911-021-01621-8","pdf_url":"https://bmcmedinformdecismak.biomedcentral.com/track/pdf/10.1186/s12911-021-01621-8","source":{"id":"https://openalex.org/S107516304","display_name":"BMC Medical Informatics and Decision Making","issn_l":"1472-6947","issn":["1472-6947"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Medical Informatics and Decision Making","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8600000143051147,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3198156935.pdf","grobid_xml":"https://content.openalex.org/works/W3198156935.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W630532510","https://openalex.org/W1489181569","https://openalex.org/W1521626219","https://openalex.org/W1819903106","https://openalex.org/W1906341845","https://openalex.org/W2064675550","https://openalex.org/W2124807415","https://openalex.org/W2126913767","https://openalex.org/W2147262247","https://openalex.org/W2159583324","https://openalex.org/W2250876691","https://openalex.org/W2250978584","https://openalex.org/W2496235729","https://openalex.org/W2508809683","https://openalex.org/W2512924740","https://openalex.org/W2513768144","https://openalex.org/W2572474373","https://openalex.org/W2741772806","https://openalex.org/W2758884106","https://openalex.org/W2760656271","https://openalex.org/W2787646045","https://openalex.org/W2902918014","https://openalex.org/W2903035303","https://openalex.org/W2903193068","https://openalex.org/W2952103439","https://openalex.org/W2962784628","https://openalex.org/W2963212250","https://openalex.org/W2963216553","https://openalex.org/W2963281280","https://openalex.org/W2970279348","https://openalex.org/W3082675885","https://openalex.org/W3104976898","https://openalex.org/W3120124891","https://openalex.org/W3204406378","https://openalex.org/W4241178869","https://openalex.org/W4241192440","https://openalex.org/W6629226572"],"related_works":["https://openalex.org/W2883671469","https://openalex.org/W2728761353","https://openalex.org/W2786253471","https://openalex.org/W3175595715","https://openalex.org/W4293584592","https://openalex.org/W2986030184","https://openalex.org/W2104907655","https://openalex.org/W4287212313","https://openalex.org/W2985215540","https://openalex.org/W3155572818"],"abstract_inverted_index":{"BACKGROUND:":[0],"Biomedical":[1],"language":[2,83],"translation":[3,29,37,143],"requires":[4,38],"multi-lingual":[5],"fluency":[6],"as":[7,9,135,137],"well":[8],"relevant":[10],"domain":[11],"knowledge.":[12],"Such":[13],"requirements":[14],"make":[15],"it":[16],"challenging":[17],"to":[18,24,72,95,160],"train":[19],"qualified":[20],"translators":[21],"and":[22,61,97,119,132,194],"costly":[23],"generate":[25],"high-quality":[26],"translations.":[27],"Machine":[28],"represents":[30],"an":[31,92,99],"effective":[32,93],"alternative,":[33],"but":[34],"accurate":[35],"machine":[36],"large":[39],"amounts":[40],"of":[41,65,108,114,175],"in-domain":[42,168],"data.":[43],"While":[44],"such":[45],"datasets":[46],"are":[47,53,63,196],"abundant":[48],"in":[49,56,85],"general":[50],"domains,":[51],"they":[52],"less":[54],"accessible":[55],"the":[57,66,86,104,188],"biomedical":[58,87],"domain.":[59,88],"Chinese":[60],"English":[62],"two":[64],"most":[67],"widely":[68],"spoken":[69],"languages,":[70],"yet":[71],"our":[73],"knowledge,":[74],"a":[75,163,172],"parallel":[76,101],"corpus":[77,102,112],"does":[78],"not":[79],"exist":[80],"for":[81,149,179],"this":[82],"pair":[84],"DESCRIPTION:":[89],"We":[90,125],"developed":[91],"pipeline":[94],"acquire":[96],"process":[98],"English-Chinese":[100],"from":[103],"New":[105],"England":[106],"Journal":[107],"Medicine":[109],"(NEJM).":[110],"This":[111],"consists":[113],"about":[115],"100,000":[116],"sentence":[117,140],"pairs":[118,141],"3,000,000":[120],"tokens":[121],"on":[122,129,166,187],"each":[123],"side.":[124],"showed":[126],"that":[127],"training":[128],"out-of-domain":[130],"data":[131,169,195],"fine-tuning":[133],"with":[134,171],"few":[136],"4000":[138],"NEJM":[139],"improve":[142,161],"quality":[144,158],"by":[145],"25.3":[146],"(13.4)":[147],"BLEU":[148,178],"en[Formula:":[150,180],"see":[151,154,181,184],"text]zh":[152,182],"(zh[Formula:":[153,183],"text]en)":[155,185],"directions.":[156],"Translation":[157],"continues":[159],"at":[162,198],"slower":[164],"pace":[165],"larger":[167],"subsets,":[170],"total":[173],"increase":[174],"33.0":[176],"(24.3)":[177],"directions":[186],"full":[189],"dataset.":[190],"CONCLUSIONS:":[191],"The":[192],"code":[193],"available":[197],"https://github.com/boxiangliu/ParaMed":[199],".":[200]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}
