{"id":"https://openalex.org/W2954075147","doi":"https://doi.org/10.1093/bioinformatics/btz528","title":"HUNER: improving biomedical NER with pretraining","display_name":"HUNER: improving biomedical NER with pretraining","publication_year":2019,"publication_date":"2019-06-25","ids":{"openalex":"https://openalex.org/W2954075147","doi":"https://doi.org/10.1093/bioinformatics/btz528","mag":"2954075147","pmid":"https://pubmed.ncbi.nlm.nih.gov/31243432"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btz528","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz528","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/36/1/295/48981302/bioinformatics_36_1_295.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"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":null,"license_id":null,"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":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/36/1/295/48981302/bioinformatics_36_1_295.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041680406","display_name":"Leon Weber","orcid":"https://orcid.org/0000-0002-2499-472X"},"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":true,"raw_author_name":"Leon Weber","raw_affiliation_strings":["Computer Science Department, Humboldt-Universit\u00e4t zu Berlin , Berlin 10099, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Humboldt-Universit\u00e4t zu Berlin , Berlin 10099, Germany","institution_ids":["https://openalex.org/I39343248"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070254031","display_name":"Jannes M\u00fcnchmeyer","orcid":"https://orcid.org/0000-0002-4006-9673"},"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"]},{"id":"https://openalex.org/I4210152878","display_name":"GFZ Helmholtz Centre for Geosciences","ror":"https://ror.org/04z8jg394","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I4210152878"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Jannes M\u00fcnchmeyer","raw_affiliation_strings":["Computer Science Department, Humboldt-Universit\u00e4t zu Berlin , Berlin 10099, Germany","Seismology Section, Helmholtzzentrum Potsdam, Deutsches GeoForschungsZentrum GFZ , Potsdam 14473, Germany","Seismology Section, Helmholtzzentrum Potsdam, Deutsches GeoForschungsZentrum GFZ, Potsdam 14473, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Humboldt-Universit\u00e4t zu Berlin , Berlin 10099, Germany","institution_ids":["https://openalex.org/I39343248"]},{"raw_affiliation_string":"Seismology Section, Helmholtzzentrum Potsdam, Deutsches GeoForschungsZentrum GFZ , Potsdam 14473, Germany","institution_ids":["https://openalex.org/I4210152878"]},{"raw_affiliation_string":"Seismology Section, Helmholtzzentrum Potsdam, Deutsches GeoForschungsZentrum GFZ, Potsdam 14473, Germany","institution_ids":["https://openalex.org/I4210152878"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079315903","display_name":"Tim Rockt\u00e4schel","orcid":null},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tim Rockt\u00e4schel","raw_affiliation_strings":["Department of Computer Science, University College London , London WC1E 6BT, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University College London , London WC1E 6BT, UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086385635","display_name":"Maryam Habibi","orcid":"https://orcid.org/0000-0002-3237-5080"},"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":"Maryam Habibi","raw_affiliation_strings":["Computer Science Department, Humboldt-Universit\u00e4t zu Berlin , Berlin 10099, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, 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":["Computer Science Department, Humboldt-Universit\u00e4t zu Berlin , Berlin 10099, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Humboldt-Universit\u00e4t zu Berlin , Berlin 10099, Germany","institution_ids":["https://openalex.org/I39343248"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5041680406","https://openalex.org/A5070254031"],"corresponding_institution_ids":["https://openalex.org/I39343248","https://openalex.org/I4210152878"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":3.3143,"has_fulltext":true,"cited_by_count":58,"citation_normalized_percentile":{"value":0.93289576,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"36","issue":"1","first_page":"295","last_page":"302"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.5389999747276306,"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":0.5389999747276306,"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":0.27410000562667847,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.08389999717473984,"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":0.649391233921051},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3937537670135498},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3514399528503418}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.649391233921051},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3937537670135498},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3514399528503418}],"mesh":[{"descriptor_ui":"D000078332","descriptor_name":"Data Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000078332","descriptor_name":"Data Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000078332","descriptor_name":"Data Analysis","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":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/btz528","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz528","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/36/1/295/48981302/bioinformatics_36_1_295.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:31243432","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31243432","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:gfzpublic.gfz-potsdam.de:item_4362895","is_oa":true,"landing_page_url":"https://gfzpublic.gfz-potsdam.de/pubman/item/item_4362895","pdf_url":null,"source":{"id":"https://openalex.org/S4306401313","display_name":"Publication Database GFZ (GFZ German Research Centre for Geosciences)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210152878","host_organization_name":"GFZ Helmholtz Centre for Geosciences","host_organization_lineage":["https://openalex.org/I4210152878"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:gfzpublic.gfz.de:item_4362895","is_oa":true,"landing_page_url":"https://gfzpublic.gfz.de/pubman/item/item_4362895","pdf_url":null,"source":{"id":"https://openalex.org/S4306401313","display_name":"Publication Database GFZ (GFZ German Research Centre for Geosciences)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210152878","host_organization_name":"GFZ Helmholtz Centre for Geosciences","host_organization_lineage":["https://openalex.org/I4210152878"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btz528","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz528","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/36/1/295/48981302/bioinformatics_36_1_295.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Partnerships for the goals","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/17"}],"awards":[{"id":"https://openalex.org/G143618889","display_name":null,"funder_award_id":"GRK 1651/2","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G4909620690","display_name":null,"funder_award_id":"LE 1428/7-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G5884421819","display_name":null,"funder_award_id":"031L0023A","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2954075147.pdf","grobid_xml":"https://content.openalex.org/works/W2954075147.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1610821757","https://openalex.org/W1850794217","https://openalex.org/W1850865022","https://openalex.org/W1964670939","https://openalex.org/W2005058680","https://openalex.org/W2040298461","https://openalex.org/W2048059249","https://openalex.org/W2064675550","https://openalex.org/W2071879021","https://openalex.org/W2080848531","https://openalex.org/W2097678794","https://openalex.org/W2100627415","https://openalex.org/W2145870108","https://openalex.org/W2151025545","https://openalex.org/W2154142897","https://openalex.org/W2162442688","https://openalex.org/W2164394614","https://openalex.org/W2165698076","https://openalex.org/W2169099542","https://openalex.org/W2169491861","https://openalex.org/W2229453122","https://openalex.org/W2346452181","https://openalex.org/W2734608416","https://openalex.org/W2949176808","https://openalex.org/W4233456913","https://openalex.org/W6636556141","https://openalex.org/W6704842505"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"MOTIVATION:":[0],"Several":[1],"recent":[2],"studies":[3],"showed":[4],"that":[5],"the":[6,13,24,29,36,48,66,129,138,152,165,175,240],"application":[7],"of":[8,31,38,108],"deep":[9,73],"neural":[10,74],"networks":[11],"advanced":[12],"state-of-the-art":[14,166],"in":[15,47,106,193,225,239],"named":[16],"entity":[17,100,149,176],"recognition":[18],"(NER),":[19],"including":[20,228],"biomedical":[21,49,99],"NER.":[22],"However,":[23],"impact":[25],"on":[26,35,85,133,174],"performance":[27],"and":[28,121,169,180,200,202,219,232],"robustness":[30],"improvements":[32],"crucially":[33],"depends":[34],"availability":[37],"sufficiently":[39],"large":[40],"training":[41],"corpora,":[42],"which":[43,156],"is":[44,186],"a":[45,72,79,86],"problem":[46,69],"domain":[50],"with":[51,119],"its":[52],"often":[53],"rather":[54,80],"small":[55],"gold":[56],"standard":[57],"corpora.":[58],"RESULTS:":[59],"We":[60,116,211],"evaluate":[61],"different":[62,94,98],"methods":[63],"for":[64,147,160,217],"alleviating":[65],"data":[67,245],"sparsity":[68],"by":[70,78,171],"pretraining":[71],"network":[75],"(LSTM-CRF),":[76],"followed":[77],"short":[81],"fine-tuning":[82],"phase":[83],"focusing":[84],"particular":[87],"corpus.":[88],"Experiments":[89],"were":[90],"performed":[91],"using":[92],"34":[93,222],"corpora":[95,223],"covering":[96],"five":[97,148],"types,":[101],"yielding":[102],"an":[103,214],"average":[104],"increase":[105],"F1-score":[107],"\u223c2":[109],"pp":[110,173],"compared":[111],"to":[112,125,198,208,235],"learning":[113],"without":[114],"pretraining.":[115],"experimented":[117],"both":[118],"supervised":[120],"semi-supervised":[122],"pretraining,":[123],"leading":[124],"interesting":[126],"insights":[127],"into":[128],"precision/recall":[130],"trade-off.":[131],"Based":[132],"our":[134,226],"results,":[135],"we":[136],"created":[137],"stand-alone":[139],"NER":[140],"tool":[141,216],"HUNER":[142,185,191],"incorporating":[143],"fully":[144],"trained":[145],"models":[146],"types.":[150],"On":[151],"independent":[153],"CRAFT":[154],"corpus,":[155],"was":[157],"not":[158],"used":[159,224],"creating":[161],"HUNER,":[162],"it":[163,196,203],"outperforms":[164],"tools":[167],"GNormPlus":[168],"tmChem":[170],"5-13":[172],"types":[177],"chemicals,":[178],"species":[179],"genes.":[181],"AVAILABILITY":[182],"AND":[183],"IMPLEMENTATION:":[184],"freely":[187],"available":[188,247],"at":[189,248],"https://hu-ner.github.io.":[190],"comes":[192],"containers,":[194],"making":[195],"easy":[197],"install":[199],"use,":[201],"can":[204],"be":[205],"applied":[206],"off-the-shelf":[207],"arbitrary":[209],"texts.":[210],"also":[212],"provide":[213],"integrated":[215],"obtaining":[218],"converting":[220],"all":[221],"evaluation,":[227],"fixed":[229],"training,":[230],"development":[231],"test":[233],"splits":[234],"enable":[236],"fair":[237],"comparisons":[238],"future.":[241],"SUPPLEMENTARY":[242],"INFORMATION:":[243],"Supplementary":[244],"are":[246],"Bioinformatics":[249],"online.":[250]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
