{"id":"https://openalex.org/W2950021574","doi":"https://doi.org/10.1093/bioinformatics/btz504","title":"Towards reliable named entity recognition in the biomedical domain","display_name":"Towards reliable named entity recognition in the biomedical domain","publication_year":2019,"publication_date":"2019-06-17","ids":{"openalex":"https://openalex.org/W2950021574","doi":"https://doi.org/10.1093/bioinformatics/btz504","mag":"2950021574","pmid":"https://pubmed.ncbi.nlm.nih.gov/31218364"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btz504","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz504","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/36/1/280/48981640/bioinformatics_36_1_280.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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","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":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/36/1/280/48981640/bioinformatics_36_1_280.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071356121","display_name":"John Giorgi","orcid":"https://orcid.org/0000-0001-9621-5046"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"John M Giorgi","raw_affiliation_strings":["Department of Computer Science, University of Toronto , Toronto, ON M5S 3G4, Canada","The Donnelly Centre, University of Toronto , Toronto, ON M5S 3E1, Canada"],"raw_orcid":"https://orcid.org/0000-0001-9621-5046","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto , Toronto, ON M5S 3G4, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"The Donnelly Centre, University of Toronto , Toronto, ON M5S 3E1, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010789029","display_name":"Gary D. Bader","orcid":"https://orcid.org/0000-0003-0185-8861"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Gary D Bader","raw_affiliation_strings":["Department of Computer Science, University of Toronto , Toronto, ON M5S 3G4, Canada","Department of Molecular Genetics, University of Toronto , Toronto, ON M5S 1A8, Canada","The Donnelly Centre, University of Toronto , Toronto, ON M5S 3E1, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Toronto , Toronto, ON M5S 3G4, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"Department of Molecular Genetics, University of Toronto , Toronto, ON M5S 1A8, Canada","institution_ids":["https://openalex.org/I185261750"]},{"raw_affiliation_string":"The Donnelly Centre, University of Toronto , Toronto, ON M5S 3E1, Canada","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5071356121"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":9.3357,"has_fulltext":true,"cited_by_count":89,"citation_normalized_percentile":{"value":0.98232827,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"36","issue":"1","first_page":"280","last_page":"286"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.53329998254776,"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":0.53329998254776,"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":0.24469999969005585,"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":0.11389999836683273,"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/crfs","display_name":"CRFS","score":0.9151990413665771},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.9105396270751953},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8303447961807251},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7453281283378601},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.6936162710189819},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6715584993362427},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.6678125262260437},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6094138622283936},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.581798791885376},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5518010854721069},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5449309945106506},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5341120958328247},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.48022064566612244},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.47655656933784485},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4523521065711975},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.41331204771995544}],"concepts":[{"id":"https://openalex.org/C2775953691","wikidata":"https://www.wikidata.org/wiki/Q5013874","display_name":"CRFS","level":3,"score":0.9151990413665771},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.9105396270751953},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8303447961807251},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7453281283378601},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.6936162710189819},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6715584993362427},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.6678125262260437},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6094138622283936},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.581798791885376},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5518010854721069},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5449309945106506},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5341120958328247},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.48022064566612244},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.47655656933784485},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4523521065711975},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.41331204771995544},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","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":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","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},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btz504","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz504","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/36/1/280/48981640/bioinformatics_36_1_280.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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:31218364","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31218364","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:europepmc.org:5915564","is_oa":false,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6956779","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btz504","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btz504","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/36/1/280/48981640/bioinformatics_36_1_280.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":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3255524790","display_name":"Pathway Commons: A Public Library of Biological Pathways","funder_award_id":"5u41hg006623-02","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G3825576971","display_name":null,"funder_award_id":"U41 HG006623","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320314000","display_name":"Compute Canada","ror":"https://ror.org/03ty8yr27"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2950021574.pdf","grobid_xml":"https://content.openalex.org/works/W2950021574.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1992593537","https://openalex.org/W1993755899","https://openalex.org/W2014849717","https://openalex.org/W2056616115","https://openalex.org/W2065963191","https://openalex.org/W2095705004","https://openalex.org/W2127479124","https://openalex.org/W2127978988","https://openalex.org/W2162888803","https://openalex.org/W2165698076","https://openalex.org/W2395579298","https://openalex.org/W2559655401","https://openalex.org/W2734608416","https://openalex.org/W2743028754","https://openalex.org/W2787068485","https://openalex.org/W2791951321","https://openalex.org/W2911489562","https://openalex.org/W2949176808","https://openalex.org/W2963339489","https://openalex.org/W3104240813","https://openalex.org/W6674330103"],"related_works":["https://openalex.org/W1964783010","https://openalex.org/W2962906565","https://openalex.org/W4250494529","https://openalex.org/W2399696375","https://openalex.org/W2798423868","https://openalex.org/W2061834489","https://openalex.org/W189110383","https://openalex.org/W2062502130","https://openalex.org/W2132038179","https://openalex.org/W2027233318"],"abstract_inverted_index":{"MOTIVATION:":[0],"Automatic":[1],"biomedical":[2,12,216],"named":[3],"entity":[4],"recognition":[5],"(BioNER)":[6],"is":[7,88,219],"a":[8,33,71,197],"key":[9],"task":[10],"in":[11,228],"information":[13],"extraction.":[14],"For":[15],"some":[16],"time,":[17],"state-of-the-art":[18],"BioNER":[19,51,103,207],"has":[20,42,125],"been":[21],"dominated":[22],"by":[23,162,169,174,191],"machine":[24],"learning":[25,113,168,173,183],"methods,":[26],"particularly":[27],"conditional":[28],"random":[29,85],"fields":[30],"(CRFs),":[31],"with":[32],"recent":[34,40],"focus":[35],"on":[36,128,137,142],"deep":[37,73],"learning.":[38,116],"However,":[39],"work":[41],"suggested":[43],"that":[44,70,122,156,203],"the":[45,59,120,129,149],"high":[46],"performance":[47,161,190],"of":[48,100,148,165],"CRFs":[49],"for":[50,102,214],"may":[52],"not":[53],"generalize":[54],"to":[55,76,104,152],"corpora":[56],"other":[57,225],"than":[58],"one":[60,138],"it":[61],"was":[62],"trained":[63],"on.":[64],"In":[65],"our":[66,146,205,215],"analysis,":[67],"we":[68,96,179,194],"find":[69],"popular":[72],"learning-based":[74],"approach":[75],"BioNER,":[77],"known":[78],"as":[79],"bidirectional":[80],"long":[81],"short-term":[82],"memory":[83],"network-conditional":[84],"field":[86],"(BiLSTM-CRF),":[87],"correspondingly":[89],"poor":[90],"at":[91,221,233,241],"generalizing.":[92],"To":[93],"address":[94],"this,":[95],"evaluate":[97],"three":[98],"modifications":[99],"BiLSTM-CRF":[101],"improve":[105],"generalization:":[106],"improved":[107],"regularization":[108],"via":[109],"variational":[110,157,185],"dropout,":[111,186],"transfer":[112,167],"and":[114,134,140,171,184,224],"multi-task":[115,172,182],"RESULTS:":[117],"We":[118,154],"measure":[119,147],"effect":[121],"each":[123],"strategy":[124],"when":[126,135],"training/testing":[127],"same":[130],"corpus":[131,139],"('in-corpus'":[132],"performance)":[133],"training":[136],"evaluating":[141],"another":[143],"('out-of-corpus'":[144],"performance),":[145],"model's":[150],"ability":[151],"generalize.":[153],"found":[155],"dropout":[158],"improves":[159],"out-of-corpus":[160,189],"an":[163],"average":[164],"4.62%,":[166],"6.48%":[170],"8.42%.":[175],"The":[176],"maximal":[177],"increase":[178],"identified":[180],"combines":[181],"which":[187],"boosts":[188],"10.75%.":[192],"Furthermore,":[193],"make":[195],"available":[196,220,232,240],"new":[198],"open-source":[199],"tool,":[200],"called":[201],"Saber":[202],"implements":[204],"best":[206],"models.":[208],"AVAILABILITY":[209],"AND":[210],"IMPLEMENTATION:":[211],"Source":[212],"code":[213],"IE":[217],"tool":[218],"https://github.com/BaderLab/saber.":[222],"Corpora":[223],"resources":[226],"used":[227],"this":[229],"study":[230],"are":[231,239],"https://github.com/BaderLab/Towards-reliable-BioNER.":[234],"SUPPLEMENTARY":[235],"INFORMATION:":[236],"Supplementary":[237],"data":[238],"Bioinformatics":[242],"online.":[243]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":22},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":5}],"updated_date":"2026-08-10T07:06:39.071514","created_date":"2025-10-10T00:00:00"}
