{"id":"https://openalex.org/W4396789721","doi":"https://doi.org/10.1007/s10579-024-09738-8","title":"Data augmentation and transfer learning for cross-lingual Named Entity Recognition in the biomedical domain","display_name":"Data augmentation and transfer learning for cross-lingual Named Entity Recognition in the biomedical domain","publication_year":2024,"publication_date":"2024-05-10","ids":{"openalex":"https://openalex.org/W4396789721","doi":"https://doi.org/10.1007/s10579-024-09738-8"},"language":"en","primary_location":{"id":"doi:10.1007/s10579-024-09738-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-024-09738-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-024-09738-8.pdf","source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","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":"Language Resources and Evaluation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10579-024-09738-8.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023032569","display_name":"Brayan Stiven Lancheros","orcid":null},"institutions":[{"id":"https://openalex.org/I119664326","display_name":"University of Wolverhampton","ror":"https://ror.org/01k2y1055","country_code":"GB","type":"education","lineage":["https://openalex.org/I119664326"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Brayan Stiven Lancheros","raw_affiliation_strings":["University of Wolverhampton, Wolverhampton, UK"],"affiliations":[{"raw_affiliation_string":"University of Wolverhampton, Wolverhampton, UK","institution_ids":["https://openalex.org/I119664326"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079590099","display_name":"Gloria Corpas Pastor","orcid":"https://orcid.org/0000-0001-6688-1531"},"institutions":[{"id":"https://openalex.org/I82767444","display_name":"Universidad de M\u00e1laga","ror":"https://ror.org/036b2ww28","country_code":"ES","type":"education","lineage":["https://openalex.org/I82767444"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Gloria Corpas Pastor","raw_affiliation_strings":["Universidad de Malaga, IUITLM, Malaga, Spain"],"affiliations":[{"raw_affiliation_string":"Universidad de Malaga, IUITLM, Malaga, Spain","institution_ids":["https://openalex.org/I82767444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020218359","display_name":"Ruslan Mitkov","orcid":null},"institutions":[{"id":"https://openalex.org/I67415387","display_name":"Lancaster University","ror":"https://ror.org/04f2nsd36","country_code":"GB","type":"education","lineage":["https://openalex.org/I67415387"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Ruslan Mitkov","raw_affiliation_strings":["Lancaster University, Lancaster, UK"],"affiliations":[{"raw_affiliation_string":"Lancaster University, Lancaster, UK","institution_ids":["https://openalex.org/I67415387"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5020218359","https://openalex.org/A5023032569"],"corresponding_institution_ids":["https://openalex.org/I119664326","https://openalex.org/I67415387"],"apc_list":null,"apc_paid":null,"fwci":1.8131,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.86640246,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"59","issue":"2","first_page":"665","last_page":"684"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9983999729156494,"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":0.9937000274658203,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.8840941190719604},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8203643560409546},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6494746208190918},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.640521228313446},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5619579553604126},{"id":"https://openalex.org/keywords/biomedical-text-mining","display_name":"Biomedical text mining","score":0.5473133325576782},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5404388308525085},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5124907493591309},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.48234814405441284},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.46542662382125854},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4148370623588562},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3956640362739563},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3816734552383423},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.2373466193675995},{"id":"https://openalex.org/keywords/text-mining","display_name":"Text mining","score":0.19840794801712036}],"concepts":[{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.8840941190719604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8203643560409546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6494746208190918},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.640521228313446},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5619579553604126},{"id":"https://openalex.org/C165141518","wikidata":"https://www.wikidata.org/wiki/Q4915126","display_name":"Biomedical text mining","level":3,"score":0.5473133325576782},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5404388308525085},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5124907493591309},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.48234814405441284},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.46542662382125854},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4148370623588562},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3956640362739563},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3816734552383423},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2373466193675995},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.19840794801712036},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10579-024-09738-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-024-09738-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-024-09738-8.pdf","source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","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":"Language Resources and Evaluation","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10579-024-09738-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10579-024-09738-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10579-024-09738-8.pdf","source":{"id":"https://openalex.org/S4306424877","display_name":"Language Resources and Evaluation","issn_l":"1574-020X","issn":["1574-020X","1574-0218"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","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":"Language Resources and Evaluation","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4396789721.pdf"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W189110383","https://openalex.org/W1533057952","https://openalex.org/W1779769545","https://openalex.org/W1970761617","https://openalex.org/W2040298461","https://openalex.org/W2048140075","https://openalex.org/W2080856991","https://openalex.org/W2148540243","https://openalex.org/W2149369282","https://openalex.org/W2169099542","https://openalex.org/W2346452181","https://openalex.org/W2414378847","https://openalex.org/W2743028754","https://openalex.org/W2757931423","https://openalex.org/W2767691613","https://openalex.org/W2809067504","https://openalex.org/W2889326796","https://openalex.org/W2911448018","https://openalex.org/W2911489562","https://openalex.org/W2915623326","https://openalex.org/W2963339489","https://openalex.org/W2963442256","https://openalex.org/W2970035587","https://openalex.org/W2970587837","https://openalex.org/W2970726011","https://openalex.org/W2970771982","https://openalex.org/W2985294119","https://openalex.org/W2985777934","https://openalex.org/W2987972786","https://openalex.org/W2989464093","https://openalex.org/W2992843255","https://openalex.org/W2997394673","https://openalex.org/W3028004046","https://openalex.org/W3034786336","https://openalex.org/W3082700373","https://openalex.org/W3096590546","https://openalex.org/W3106224367","https://openalex.org/W3109296849","https://openalex.org/W3120712761","https://openalex.org/W4235109031","https://openalex.org/W4290928197"],"related_works":["https://openalex.org/W2334378031","https://openalex.org/W2134429551","https://openalex.org/W2916255597","https://openalex.org/W2017675085","https://openalex.org/W4396918568","https://openalex.org/W2548624545","https://openalex.org/W2999302224","https://openalex.org/W3091569222","https://openalex.org/W3004288456","https://openalex.org/W4379379356"],"abstract_inverted_index":{"Abstract":[0],"Given":[1],"the":[2,9,13,17,19,71,77,112,127,155,168,188,191,212,219,229,246,254],"increase":[3],"in":[4,41,76,99,134,157,175,190,228,242],"production":[5],"of":[6,16,34,58,64,74,84,90,95,121,129,167,187,205,216,236],"data":[7,108,131],"for":[8,21,39,53,132,136],"biomedical":[10,49,59,65,78,96,130],"field":[11],"and":[12,56,67,93,115,207,251],"unstoppable":[14],"growth":[15],"internet,":[18],"need":[20],"Information":[22],"Extraction":[23],"(IE)":[24],"techniques":[25],"has":[26,80,253],"skyrocketed.":[27],"Named":[28],"Entity":[29],"Recognition":[30],"(NER)":[31],"is":[32,51,124,182],"one":[33],"such":[35],"IE":[36],"tasks":[37],"useful":[38],"professionals":[40],"different":[42],"areas.":[43],"There":[44],"are":[45],"several":[46],"settings":[47],"where":[48],"NER":[50,97,133,147,226,249],"needed,":[52],"instance,":[54],"extraction":[55],"analysis":[57],"literature,":[60],"relation":[61],"extraction,":[62],"organisation":[63],"documents,":[66],"knowledge-base":[68],"completion.":[69],"However,":[70],"computational":[72],"treatment":[73],"entities":[75,189],"domain":[79,113],"faced":[81],"a":[82,144,164,178,195],"number":[83],"challenges":[85],"including":[86],"its":[87,116],"high":[88],"cost":[89],"annotation,":[91],"ambiguity,":[92],"lack":[94],"datasets":[98,140,206],"languages":[100],"other":[101],"than":[102],"English.":[103],"These":[104],"difficulties":[105],"have":[106],"hampered":[107],"development,":[109],"affecting":[110],"both":[111],"itself":[114],"multilingual":[117],"coverage.":[118],"The":[119,223,238],"purpose":[120],"this":[122,152,243],"study":[123],"to":[125,162,210,256],"overcome":[126],"scarcity":[128],"Spanish,":[135],"which":[137],"only":[138],"two":[139,201],"exist,":[141],"by":[142,150,184],"developing":[143],"robust":[145],"bilingual":[146,248],"model.":[148],"Inspired":[149],"back-translation,":[151],"paper":[153,244],"leverages":[154],"progress":[156],"Neural":[158],"Machine":[159],"Translation":[160],"(NMT)":[161],"create":[163],"synthetic":[165],"version":[166],"Colorado":[169],"Richly":[170],"Annotated":[171],"Full-Text":[172],"(CRAFT)":[173],"dataset":[174,181,193],"Spanish.":[176],"Additionally,":[177],"new":[179,196],"CRAFT":[180],"constructed":[183],"replacing":[185],"20%":[186],"original":[192],"generating":[194],"augmented":[197],"dataset.":[198],"We":[199],"evaluate":[200],"training":[202,209],"methods:":[203],"concatenation":[204],"continuous":[208],"assess":[211],"transfer":[213],"learning":[214],"capabilities":[215],"transformers":[217],"using":[218],"newly":[220],"obtained":[221],"datasets.":[222],"best":[224],"performing":[225],"system":[227,250],"development":[230],"set":[231],"achieved":[232],"an":[233],"F-1":[234],"score":[235],"86.39%.":[237],"novel":[239],"methodology":[240],"proposed":[241],"presents":[245],"first":[247],"it":[252],"potential":[255],"improve":[257],"applications":[258],"across":[259],"under-resourced":[260],"languages.":[261]},"counts_by_year":[{"year":2025,"cited_by_count":5}],"updated_date":"2025-11-20T23:13:51.555489","created_date":"2025-10-10T00:00:00"}