{"id":"https://openalex.org/W4402697996","doi":"https://doi.org/10.1093/bioinformatics/btae564","title":"HunFlair2 in a cross-corpus evaluation of biomedical named entity recognition and normalization tools","display_name":"HunFlair2 in a cross-corpus evaluation of biomedical named entity recognition and normalization tools","publication_year":2024,"publication_date":"2024-09-20","ids":{"openalex":"https://openalex.org/W4402697996","doi":"https://doi.org/10.1093/bioinformatics/btae564","pmid":"https://pubmed.ncbi.nlm.nih.gov/39302686"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btae564","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae564","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/40/10/btae564/59604134/btae564.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/40/10/btae564/59604134/btae564.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017484078","display_name":"Mario S\u00e4nger","orcid":"https://orcid.org/0000-0002-2950-2587"},"institutions":[{"id":"https://openalex.org/I39343248","display_name":"Humboldt-Universit\u00e4t zu Berlin","ror":"https://ror.org/01hcx6992","country_code":"DE","type":"education","lineage":["https://openalex.org/I39343248"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mario S\u00e4nger","raw_affiliation_strings":["Department of Computer Science, Humboldt-Universit\u00e4t zu Berlin , Berlin 10099,","Department of Computer Science, Humboldt-Universit\u00e4t zu Berlin, Berlin, 10099, Germany"],"raw_orcid":"https://orcid.org/0000-0002-2950-2587","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Humboldt-Universit\u00e4t zu Berlin , Berlin 10099,","institution_ids":["https://openalex.org/I39343248"]},{"raw_affiliation_string":"Department of Computer Science, Humboldt-Universit\u00e4t zu Berlin, Berlin, 10099, Germany","institution_ids":["https://openalex.org/I39343248"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053986488","display_name":"Samuele Garda","orcid":null},"institutions":[{"id":"https://openalex.org/I39343248","display_name":"Humboldt-Universit\u00e4t zu Berlin","ror":"https://ror.org/01hcx6992","country_code":"DE","type":"education","lineage":["https://openalex.org/I39343248"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Samuele Garda","raw_affiliation_strings":["Department of Computer Science, Humboldt-Universit\u00e4t zu Berlin , Berlin 10099,","Department of Computer Science, Humboldt-Universit\u00e4t zu Berlin, Berlin, 10099, Germany"],"raw_orcid":"https://orcid.org/0009-0002-8234-8299","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Humboldt-Universit\u00e4t zu Berlin , Berlin 10099,","institution_ids":["https://openalex.org/I39343248"]},{"raw_affiliation_string":"Department of Computer Science, Humboldt-Universit\u00e4t zu Berlin, Berlin, 10099, Germany","institution_ids":["https://openalex.org/I39343248"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026330539","display_name":"Xing David Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I39343248","display_name":"Humboldt-Universit\u00e4t zu Berlin","ror":"https://ror.org/01hcx6992","country_code":"DE","type":"education","lineage":["https://openalex.org/I39343248"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Xing David Wang","raw_affiliation_strings":["Department of Computer Science, Humboldt-Universit\u00e4t zu Berlin , Berlin 10099,","Department of Computer Science, Humboldt-Universit\u00e4t zu Berlin, Berlin, 10099, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Humboldt-Universit\u00e4t zu Berlin , Berlin 10099,","institution_ids":["https://openalex.org/I39343248"]},{"raw_affiliation_string":"Department of Computer Science, Humboldt-Universit\u00e4t zu Berlin, Berlin, 10099, Germany","institution_ids":["https://openalex.org/I39343248"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041680406","display_name":"Leon Weber","orcid":"https://orcid.org/0000-0002-2499-472X"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Leon Weber-Genzel","raw_affiliation_strings":["Center for Information and Language Processing (CIS), Ludwig Maximilian University Munich , M\u00fcnchen 80539,","Center for Information and Language Processing (CIS), Ludwig Maximilian University Munich, M\u00fcnchen, 80539, Germany"],"raw_orcid":"https://orcid.org/0000-0002-2499-472X","affiliations":[{"raw_affiliation_string":"Center for Information and Language Processing (CIS), Ludwig Maximilian University Munich , M\u00fcnchen 80539,","institution_ids":["https://openalex.org/I8204097"]},{"raw_affiliation_string":"Center for Information and Language Processing (CIS), Ludwig Maximilian University Munich, M\u00fcnchen, 80539, Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093975915","display_name":"Pia Droop","orcid":null},"institutions":[{"id":"https://openalex.org/I39343248","display_name":"Humboldt-Universit\u00e4t zu Berlin","ror":"https://ror.org/01hcx6992","country_code":"DE","type":"education","lineage":["https://openalex.org/I39343248"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Pia Droop","raw_affiliation_strings":["Department of Computer Science, Humboldt-Universit\u00e4t zu Berlin , Berlin 10099,","Department of Computer Science, Humboldt-Universit\u00e4t zu Berlin, Berlin, 10099, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Humboldt-Universit\u00e4t zu Berlin , Berlin 10099,","institution_ids":["https://openalex.org/I39343248"]},{"raw_affiliation_string":"Department of Computer Science, Humboldt-Universit\u00e4t zu Berlin, Berlin, 10099, Germany","institution_ids":["https://openalex.org/I39343248"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082908843","display_name":"Benedikt Fuchs","orcid":null},"institutions":[{"id":"https://openalex.org/I4210163259","display_name":"Forschungs- und Beratungsstelle Arbeitswelt","ror":"https://ror.org/05yb1mg89","country_code":"AT","type":"facility","lineage":["https://openalex.org/I4210163259"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Benedikt Fuchs","raw_affiliation_strings":["Research Industrial Systems Engineering (RISE) Forschungs-, Entwicklungs- und Gro\u00dfprojektberatung GmbH , Schwechat 2320,","Research Industrial Systems Engineering (RISE) Forschungs-, Entwicklungs- und Gro\u00dfprojektberatung GmbH, Schwechat, 2320, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Industrial Systems Engineering (RISE) Forschungs-, Entwicklungs- und Gro\u00dfprojektberatung GmbH , Schwechat 2320,","institution_ids":["https://openalex.org/I4210163259"]},{"raw_affiliation_string":"Research Industrial Systems Engineering (RISE) Forschungs-, Entwicklungs- und Gro\u00dfprojektberatung GmbH, Schwechat, 2320, Austria","institution_ids":["https://openalex.org/I4210163259"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032877157","display_name":"Alan Akbik","orcid":null},"institutions":[{"id":"https://openalex.org/I39343248","display_name":"Humboldt-Universit\u00e4t zu Berlin","ror":"https://ror.org/01hcx6992","country_code":"DE","type":"education","lineage":["https://openalex.org/I39343248"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alan Akbik","raw_affiliation_strings":["Department of Computer Science, Humboldt-Universit\u00e4t zu Berlin , Berlin 10099,","Department of Computer Science, Humboldt-Universit\u00e4t zu Berlin, Berlin, 10099, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Humboldt-Universit\u00e4t zu Berlin , Berlin 10099,","institution_ids":["https://openalex.org/I39343248"]},{"raw_affiliation_string":"Department of Computer Science, Humboldt-Universit\u00e4t zu Berlin, Berlin, 10099, Germany","institution_ids":["https://openalex.org/I39343248"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055236937","display_name":"Ulf Leser","orcid":"https://orcid.org/0000-0003-2166-9582"},"institutions":[{"id":"https://openalex.org/I39343248","display_name":"Humboldt-Universit\u00e4t zu Berlin","ror":"https://ror.org/01hcx6992","country_code":"DE","type":"education","lineage":["https://openalex.org/I39343248"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ulf Leser","raw_affiliation_strings":["Department of Computer Science, Humboldt-Universit\u00e4t zu Berlin , Berlin 10099,","Department of Computer Science, Humboldt-Universit\u00e4t zu Berlin, Berlin, 10099, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Humboldt-Universit\u00e4t zu Berlin , Berlin 10099,","institution_ids":["https://openalex.org/I39343248"]},{"raw_affiliation_string":"Department of Computer Science, Humboldt-Universit\u00e4t zu Berlin, Berlin, 10099, Germany","institution_ids":["https://openalex.org/I39343248"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":3.2093,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.92655276,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"40","issue":"10","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9797999858856201,"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":0.9797999858856201,"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":0.013700000010430813,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.0005000000237487257,"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/normalization","display_name":"Normalization (sociology)","score":0.8107193112373352},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7899688482284546},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.6625634431838989},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6421521902084351},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5965254306793213},{"id":"https://openalex.org/keywords/named-entity","display_name":"Named entity","score":0.5451478362083435},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5053889751434326},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4824410080909729},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.46601182222366333},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.4571928083896637},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.44538113474845886},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.44342461228370667},{"id":"https://openalex.org/keywords/biomedical-text-mining","display_name":"Biomedical text mining","score":0.433065265417099},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4277958869934082},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4183982312679291},{"id":"https://openalex.org/keywords/text-mining","display_name":"Text mining","score":0.2725251317024231},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.09216055274009705}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8107193112373352},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7899688482284546},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.6625634431838989},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6421521902084351},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5965254306793213},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.5451478362083435},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5053889751434326},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4824410080909729},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.46601182222366333},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.4571928083896637},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.44538113474845886},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.44342461228370667},{"id":"https://openalex.org/C165141518","wikidata":"https://www.wikidata.org/wiki/Q4915126","display_name":"Biomedical text mining","level":3,"score":0.433065265417099},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4277958869934082},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4183982312679291},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.2725251317024231},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.09216055274009705},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[{"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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btae564","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae564","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/40/10/btae564/59604134/btae564.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:39302686","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39302686","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11453098","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11453098","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11453098/pdf/btae564.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":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btae564","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btae564","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/40/10/btae564/59604134/btae564.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5199999809265137,"display_name":"Responsible consumption and production","id":"https://metadata.un.org/sdg/12"}],"awards":[{"id":"https://openalex.org/G5302700050","display_name":null,"funder_award_id":"RTG2424","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G5729854464","display_name":"Eidetische Repr\u00e4sentationen Nat\u00fcrlicher Sprache","funder_award_id":"448414230","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G6510858048","display_name":"EXC 2002: Science of Intelligence (SCIoI)","funder_award_id":"390523135","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G6532450817","display_name":null,"funder_award_id":"EXC 2002","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402697996.pdf","grobid_xml":"https://content.openalex.org/works/W4402697996.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1610821757","https://openalex.org/W1666916593","https://openalex.org/W2032584931","https://openalex.org/W2052250375","https://openalex.org/W2060942759","https://openalex.org/W2071879021","https://openalex.org/W2100627415","https://openalex.org/W2115610681","https://openalex.org/W2127563440","https://openalex.org/W2129113459","https://openalex.org/W2142678031","https://openalex.org/W2159583324","https://openalex.org/W2414378847","https://openalex.org/W2761714433","https://openalex.org/W2791951321","https://openalex.org/W2946690328","https://openalex.org/W2950021574","https://openalex.org/W3040936192","https://openalex.org/W3045642779","https://openalex.org/W3087801495","https://openalex.org/W3125468681","https://openalex.org/W3137481621","https://openalex.org/W3156936474","https://openalex.org/W3173561451","https://openalex.org/W3186054896","https://openalex.org/W4221142212","https://openalex.org/W4226265641","https://openalex.org/W4241410814","https://openalex.org/W4283318325","https://openalex.org/W4296777576","https://openalex.org/W4297458751","https://openalex.org/W4309659061","https://openalex.org/W4311903220","https://openalex.org/W4323519786","https://openalex.org/W4376274483","https://openalex.org/W4379197269","https://openalex.org/W4388775058","https://openalex.org/W4393094733","https://openalex.org/W6838616034","https://openalex.org/W6926259797"],"related_works":["https://openalex.org/W2186562580","https://openalex.org/W2155874911","https://openalex.org/W4255258373","https://openalex.org/W2593907245","https://openalex.org/W2032007337","https://openalex.org/W3000685722","https://openalex.org/W3006227201","https://openalex.org/W3091569222","https://openalex.org/W2901060953","https://openalex.org/W2899463504"],"abstract_inverted_index":{"MOTIVATION:":[0],"With":[1],"the":[2,6,21,71,84,111,114,127,141,214,218,224,228,253,284],"exponential":[3],"growth":[4],"of":[5,23,29,126,143,170,223,244],"life":[7],"sciences":[8],"literature,":[9],"biomedical":[10],"text":[11,89,107],"mining":[12],"(BTM)":[13],"has":[14],"become":[15],"an":[16,187],"essential":[17],"technology":[18],"for":[19,63,99,133,149,186,270],"accelerating":[20],"extraction":[22],"insights":[24],"from":[25,58,91,96],"publications.":[26],"The":[27],"identification":[28],"entities":[30],"in":[31,44,50,70,74,103,260],"texts,":[32],"such":[33],"as":[34],"diseases":[35],"or":[36,106],"genes,":[37],"and":[38,121,152,184,205,220,263],"their":[39,164],"normalization,":[40,153],"i.e.":[41,86],"grounding":[42],"them":[43],"knowledge":[45],"base,":[46],"are":[47,67,81,281],"crucial":[48],"steps":[49,66],"any":[51],"BTM":[52,245,273],"pipeline":[53],"to":[54,93,159,293],"enable":[55],"information":[56],"aggregation":[57],"multiple":[59],"documents.":[60],"However,":[61],"tools":[62,155,246,259],"these":[64],"two":[65],"rarely":[68],"applied":[69,82,157],"same":[72,128],"context":[73],"which":[75],"they":[76,80],"were":[77,156],"developed.":[78],"Instead,":[79],"\"in":[83],"wild,\"":[85],"on":[87,123,140,167,178,190,231],"application-dependent":[88],"collections":[90],"moderately":[92],"extremely":[94],"different":[95,124],"those":[97],"used":[98,162],"training,":[100],"varying,":[101],"e.g.":[102],"focus,":[104],"genre":[105],"type.":[108],"This":[109],"raises":[110],"question":[112],"whether":[113],"reported":[115],"performance,":[116],"usually":[117],"obtained":[118],"by":[119,236],"training":[120],"evaluating":[122],"partitions":[125],"corpus,":[129],"can":[130],"be":[131],"trusted":[132],"downstream":[134],"applications.":[135],"RESULTS:":[136],"Here,":[137],"we":[138,174],"report":[139],"results":[142,200,240,296],"a":[144,168,202,249],"carefully":[145],"designed":[146],"cross-corpus":[147,208],"benchmark":[148],"entity":[150,197],"recognition":[151],"where":[154],"systematically":[158],"corpora":[160,194],"not":[161],"during":[163],"training.":[165],"Based":[166],"survey":[169],"28":[171],"published":[172,255],"systems,":[173],"selected":[175],"five,":[176],"based":[177],"predefined":[179],"criteria":[180],"like":[181],"feature":[182],"richness":[183],"availability,":[185],"in-depth":[188],"analysis":[189],"three":[191],"publicly":[192],"available":[193,298],"covering":[195],"four":[196],"types.":[198],"Our":[199,239],"present":[201],"mixed":[203],"picture":[204],"show":[206,264],"that":[207,242,265],"performance":[209,230,251],"is":[210,268,297],"significantly":[211],"lower":[212,250],"than":[213,252],"in-corpus":[215],"performance.":[216],"HunFlair2,":[217],"redesigned":[219],"extended":[221],"successor":[222],"HunFlair":[225],"tool,":[226],"showed":[227],"best":[229],"average,":[232],"being":[233],"closely":[234],"followed":[235],"PubTator":[237],"Central.":[238],"indicate":[241],"users":[243],"should":[247],"expect":[248],"original":[254],"one":[256],"when":[257],"applying":[258],"\"the":[261],"wild\"":[262],"further":[266],"research":[267],"necessary":[269],"more":[271],"robust":[272],"tools.":[274],"AVAILABILITY":[275],"AND":[276],"IMPLEMENTATION:":[277],"All":[278],"our":[279,295],"models":[280],"integrated":[282],"into":[283],"Natural":[285],"Language":[286],"Processing":[287],"(NLP)":[288],"framework":[289],"flair:":[290],"https://github.com/flairNLP/flair.":[291],"Code":[292],"reproduce":[294],"at:":[299],"https://github.com/hu-ner/hunflair2-experiments.":[300]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}
