{"id":"https://openalex.org/W2791951321","doi":"https://doi.org/10.1093/bioinformatics/bty152","title":"Exploiting and assessing multi-source data for supervised biomedical named entity recognition","display_name":"Exploiting and assessing multi-source data for supervised biomedical named entity recognition","publication_year":2018,"publication_date":"2018-03-08","ids":{"openalex":"https://openalex.org/W2791951321","doi":"https://doi.org/10.1093/bioinformatics/bty152","mag":"2791951321","pmid":"https://pubmed.ncbi.nlm.nih.gov/29538614"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bty152","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bty152","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/34/14/2474/48917751/bioinformatics_34_14_2474.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","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":"hybrid","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/34/14/2474/48917751/bioinformatics_34_14_2474.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011362662","display_name":"Dieter Galea","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dieter Galea","raw_affiliation_strings":["Computational and Systems Medicine, Department of Surgery and Cancer, Faculty of Medicine, Imperial College London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational and Systems Medicine, Department of Surgery and Cancer, Faculty of Medicine, Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050041550","display_name":"Ivan Laponogov","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ivan Laponogov","raw_affiliation_strings":["Computational and Systems Medicine, Department of Surgery and Cancer, Faculty of Medicine, Imperial College London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational and Systems Medicine, Department of Surgery and Cancer, Faculty of Medicine, Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061524521","display_name":"Kirill Veselkov","orcid":"https://orcid.org/0000-0002-1164-0359"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Kirill Veselkov","raw_affiliation_strings":["Computational and Systems Medicine, Department of Surgery and Cancer, Faculty of Medicine, Imperial College London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational and Systems Medicine, Department of Surgery and Cancer, Faculty of Medicine, Imperial College London, London, UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5061524521"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":2545,"currency":"EUR","value_usd":2744},"fwci":1.5682,"has_fulltext":true,"cited_by_count":27,"citation_normalized_percentile":{"value":0.83044552,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"34","issue":"14","first_page":"2474","last_page":"2482"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9146000146865845,"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":0.9146000146865845,"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":0.060499999672174454,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.0026000000070780516,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.8472819328308105},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7081682682037354},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.680781364440918},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.6791157126426697},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6379683017730713},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6140231490135193},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5408139824867249},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4542832374572754},{"id":"https://openalex.org/keywords/named-entity","display_name":"Named entity","score":0.43216121196746826},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3393838107585907},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.15689513087272644}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8472819328308105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7081682682037354},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.680781364440918},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.6791157126426697},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6379683017730713},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6140231490135193},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5408139824867249},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4542832374572754},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.43216121196746826},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3393838107585907},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.15689513087272644},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D039781","descriptor_name":"PubMed","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D039781","descriptor_name":"PubMed","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D039781","descriptor_name":"PubMed","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","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":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":5,"locations":[{"id":"doi:10.1093/bioinformatics/bty152","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bty152","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/34/14/2474/48917751/bioinformatics_34_14_2474.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","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:29538614","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29538614","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:5001476","is_oa":true,"landing_page_url":"http://europepmc.org/pmc/articles/PMC6041968","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:6041968","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6041968","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"},{"id":"pmh:oai:spiral.imperial.ac.uk:10044/1/57872","is_oa":true,"landing_page_url":"http://hdl.handle.net/10044/1/57872","pdf_url":null,"source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"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":"2482","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/bty152","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bty152","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/34/14/2474/48917751/bioinformatics_34_14_2474.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","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7200000286102295}],"awards":[{"id":"https://openalex.org/G5827216101","display_name":"Development of a rapid bacterial identification method based on direct mass spectrometric metabolic profiling","funder_award_id":"BB/L020858/1","funder_id":"https://openalex.org/F4320334629","funder_display_name":"Biotechnology and Biological Sciences Research Council"},{"id":"https://openalex.org/G7090684953","display_name":null,"funder_award_id":"BB/L020858/1","funder_id":"https://openalex.org/F4320334629","funder_display_name":"Biotechnology and Biological Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320320283","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10"},{"id":"https://openalex.org/F4320334629","display_name":"Biotechnology and Biological Sciences Research Council","ror":"https://ror.org/00cwqg982"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2791951321.pdf","grobid_xml":"https://content.openalex.org/works/W2791951321.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1850865022","https://openalex.org/W1969099570","https://openalex.org/W1986657538","https://openalex.org/W1992593537","https://openalex.org/W2005058680","https://openalex.org/W2018874418","https://openalex.org/W2065963191","https://openalex.org/W2094344445","https://openalex.org/W2096765155","https://openalex.org/W2097960255","https://openalex.org/W2098722636","https://openalex.org/W2101819947","https://openalex.org/W2102514878","https://openalex.org/W2104148262","https://openalex.org/W2120754707","https://openalex.org/W2122496897","https://openalex.org/W2127008962","https://openalex.org/W2132886902","https://openalex.org/W2149369282","https://openalex.org/W2159640576","https://openalex.org/W2163107094","https://openalex.org/W2169918010","https://openalex.org/W2169974160","https://openalex.org/W2170189740","https://openalex.org/W2512727383","https://openalex.org/W2588444726","https://openalex.org/W2613831280","https://openalex.org/W2626176522","https://openalex.org/W2743028754","https://openalex.org/W4242191001","https://openalex.org/W6674234289","https://openalex.org/W6679893009"],"related_works":["https://openalex.org/W4308949089","https://openalex.org/W2146948107","https://openalex.org/W3101260801","https://openalex.org/W3031263788","https://openalex.org/W4226048468","https://openalex.org/W3214642209","https://openalex.org/W1980748319","https://openalex.org/W4289638072","https://openalex.org/W2405038964","https://openalex.org/W4285261719"],"abstract_inverted_index":{"Motivation:":[0],"Recognition":[1],"of":[2,12,65,90,108,134,141,151,168,198,234,246],"biomedical":[3],"entities":[4,110],"from":[5],"scientific":[6],"text":[7],"is":[8,162,227],"a":[9],"critical":[10],"component":[11],"natural":[13],"language":[14],"processing":[15],"and":[16,51,63,118,124,239,243,254],"automated":[17],"information":[18],"extraction":[19],"platforms.":[20],"Modern":[21],"named":[22,209],"entity":[23,85,121,155,210],"recognition":[24,86,107,150],"approaches":[25,42],"rely":[26],"heavily":[27],"on":[28,37,53,144],"supervised":[29],"machine":[30],"learning":[31],"techniques,":[32],"which":[33,177],"are":[34,250,260],"critically":[35],"dependent":[36],"annotated":[38,236],"training":[39,200],"corpora.":[40,159],"These":[41],"have":[43],"been":[44],"shown":[45],"to":[46,78,130,165],"perform":[47],"well":[48,186],"when":[49],"trained":[50,143],"tested":[52],"the":[54,61,106,132,152,182,195,232,235,247],"same":[55,153],"source.":[56],"However,":[57],"in":[58,82,94,157,203],"such":[59,72,96],"scenario,":[60],"performance":[62,226],"evaluation":[64],"these":[66],"models":[67,73,142,207],"may":[68,74],"be":[69],"optimistic,":[70],"as":[71,97,112,185,187],"not":[75,229],"necessarily":[76],"generalize":[77],"independent":[79,158],"corpora,":[80],"resulting":[81],"potential":[83,188],"non-optimal":[84],"for":[87,105,149,208],"large-scale":[88],"tagging":[89],"widely":[91],"diverse":[92],"articles":[93],"databases":[95],"PubMed.":[98],"Results:":[99],"Here":[100],"we":[101,178,222],"aggregated":[102,248],"published":[103],"corpora":[104,146,174,201,249],"biomolecular":[109,154],"(such":[111],"genes,":[113],"RNA,":[114],"proteins,":[115],"variants,":[116],"drugs":[117],"metabolites),":[119],"identified":[120,224],"class":[122],"overlap":[123],"performed":[125],"leave-corpus-out":[126],"cross":[127],"validation":[128],"strategy":[129],"test":[131],"efficiency":[133],"existing":[135],"models.":[136],"We":[137,192],"demonstrate":[138],"that":[139,194,225],"accuracies":[140],"individual":[145,173,215],"decrease":[147],"substantially":[148],"classes":[156],"This":[160],"behavior":[161],"possibly":[163],"due":[164],"limited":[166,230],"generalizability":[167],"entity-class-related":[169],"features":[170],"captured":[171],"by":[172,231],"(model":[175],"'overtraining')":[176],"investigated":[179],"further":[180,223],"at":[181,262],"orthographic":[183],"level,":[184],"annotation":[189],"standard":[190],"differences.":[191],"show":[193],"combined":[196],"use":[197],"multi-source":[199],"results":[202],"overall":[204],"more":[205],"generalizable":[206],"recognition,":[211],"while":[212],"achieving":[213],"comparable":[214],"performance.":[216],"By":[217],"performing":[218],"learning-curve-based":[219],"power":[220],"analysis":[221],"often":[228],"quantity":[233],"data.":[237],"Availability":[238],"implementation:":[240],"Compiled":[241],"primary":[242],"secondary":[244],"sources":[245],"available":[251,261],"on:":[252],"https://github.com/dterg/biomedical_corpora/wiki":[253],"https://bitbucket.org/iAnalytica/bioner.":[255],"Supplementary":[256,258],"information:":[257],"data":[259],"Bioinformatics":[263],"online.":[264]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-08-08T07:41:36.138363","created_date":"2025-10-10T00:00:00"}
