{"id":"https://openalex.org/W2139067830","doi":"https://doi.org/10.1186/2041-1480-4-28","title":"Evaluating gold standard corpora against gene/protein tagging solutions and lexical resources","display_name":"Evaluating gold standard corpora against gene/protein tagging solutions and lexical resources","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W2139067830","doi":"https://doi.org/10.1186/2041-1480-4-28","mag":"2139067830","pmid":"https://pubmed.ncbi.nlm.nih.gov/24112383"},"language":"en","primary_location":{"id":"doi:10.1186/2041-1480-4-28","is_oa":true,"landing_page_url":"https://doi.org/10.1186/2041-1480-4-28","pdf_url":"https://jbiomedsem.biomedcentral.com/counter/pdf/10.1186/2041-1480-4-28","source":{"id":"https://openalex.org/S172276550","display_name":"Journal of Biomedical Semantics","issn_l":"2041-1480","issn":["2041-1480"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Biomedical Semantics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jbiomedsem.biomedcentral.com/counter/pdf/10.1186/2041-1480-4-28","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006224704","display_name":"Dietrich Rebholz\u2010Schuhmann","orcid":"https://orcid.org/0000-0002-1018-0370"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]},{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]},{"id":"https://openalex.org/I87048295","display_name":"Wellcome Trust","ror":"https://ror.org/029chgv08","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I87048295"]}],"countries":["CH","GB"],"is_corresponding":true,"raw_author_name":"Dietrich Rebholz-Schuhmann","raw_affiliation_strings":["Institute of Computational Linguistics, University of Z\u00fcrich, CH-8050 Z\u00fcrich, Switzerland. rebholz@ifi.uzh.ch","Institute of Computational Linguistics, University of Z\u00fcrich, Z\u00fcrich, Switzerland","European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computational Linguistics, University of Z\u00fcrich, CH-8050 Z\u00fcrich, Switzerland. rebholz@ifi.uzh.ch","institution_ids":["https://openalex.org/I202697423"]},{"raw_affiliation_string":"Institute of Computational Linguistics, University of Z\u00fcrich, Z\u00fcrich, Switzerland","institution_ids":["https://openalex.org/I202697423"]},{"raw_affiliation_string":"European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, UK","institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I87048295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069397549","display_name":"\u015eenay Kafkas","orcid":"https://orcid.org/0000-0001-7509-5786"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]},{"id":"https://openalex.org/I87048295","display_name":"Wellcome Trust","ror":"https://ror.org/029chgv08","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I87048295"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Senay Kafkas","raw_affiliation_strings":["European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SD, UK","European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SD, UK","institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I87048295"]},{"raw_affiliation_string":"European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, UK","institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I87048295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016481961","display_name":"Jee-Hyub Kim","orcid":"https://orcid.org/0000-0002-0359-2887"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]},{"id":"https://openalex.org/I87048295","display_name":"Wellcome Trust","ror":"https://ror.org/029chgv08","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I87048295"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jee-Hyub Kim","raw_affiliation_strings":["European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SD, UK","European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SD, UK","institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I87048295"]},{"raw_affiliation_string":"European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, UK","institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I87048295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100369793","display_name":"Chen Li","orcid":"https://orcid.org/0000-0002-0079-3106"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]},{"id":"https://openalex.org/I87048295","display_name":"Wellcome Trust","ror":"https://ror.org/029chgv08","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I87048295"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chen Li","raw_affiliation_strings":["European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SD, UK","European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SD, UK","institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I87048295"]},{"raw_affiliation_string":"European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, UK","institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I87048295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077681143","display_name":"Antonio Jimeno Yepes","orcid":"https://orcid.org/0000-0002-6581-094X"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]},{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I87048295","display_name":"Wellcome Trust","ror":"https://ror.org/029chgv08","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I87048295"]}],"countries":["AU","GB"],"is_corresponding":false,"raw_author_name":"Antonio Yepes","raw_affiliation_strings":["European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SD, UK","NICTA Victoria Research Laboratory, The University of Melbourne, Wilson Ave, Melbourne, VIC, 3010, Australia","NICTA Victoria Research Laboratory, The University of Melbourne, Melbourne, Australia","European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SD, UK","institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I87048295"]},{"raw_affiliation_string":"NICTA Victoria Research Laboratory, The University of Melbourne, Wilson Ave, Melbourne, VIC, 3010, Australia","institution_ids":["https://openalex.org/I42894916"]},{"raw_affiliation_string":"NICTA Victoria Research Laboratory, The University of Melbourne, Melbourne, Australia","institution_ids":["https://openalex.org/I42894916","https://openalex.org/I165779595"]},{"raw_affiliation_string":"European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, UK","institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I87048295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043808311","display_name":"Robert Hoehndorf","orcid":"https://orcid.org/0000-0001-8149-5890"},"institutions":[{"id":"https://openalex.org/I16038530","display_name":"Aberystwyth University","ror":"https://ror.org/015m2p889","country_code":"GB","type":"education","lineage":["https://openalex.org/I16038530"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Robert Hoehndorf","raw_affiliation_strings":["Department of Computer Science, Aberystwyth University, Llandinam Building, Aberystwyth, eredigion, Wales, SY23 3DB, UK","Department of Computer Science, Aberystwyth University, eredigion, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Aberystwyth University, Llandinam Building, Aberystwyth, eredigion, Wales, SY23 3DB, UK","institution_ids":["https://openalex.org/I16038530"]},{"raw_affiliation_string":"Department of Computer Science, Aberystwyth University, eredigion, UK","institution_ids":["https://openalex.org/I16038530"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017672883","display_name":"Rolf Backofen","orcid":"https://orcid.org/0000-0001-8231-3323"},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rolf Backofen","raw_affiliation_strings":["Ludwigs-University Freiburg, Fahnenbergplatz, D-79085, Freiburg, Germany","Ludwigs-University Freiburg, Fahnenbergplatz, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ludwigs-University Freiburg, Fahnenbergplatz, D-79085, Freiburg, Germany","institution_ids":["https://openalex.org/I161046081"]},{"raw_affiliation_string":"Ludwigs-University Freiburg, Fahnenbergplatz, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088357141","display_name":"Ian Lewin","orcid":null},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]},{"id":"https://openalex.org/I4210103233","display_name":"Linguamatics (United Kingdom)","ror":"https://ror.org/019syv921","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210103233"]},{"id":"https://openalex.org/I87048295","display_name":"Wellcome Trust","ror":"https://ror.org/029chgv08","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I87048295"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ian Lewin","raw_affiliation_strings":["European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SD, UK","Linguamatics Ltd, 324 Cambridge Science Park, Milton Road, Cambridge, CB4 0WG, UK","European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, UK","Linguamatics Ltd, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, Cambridge, CB10 1SD, UK","institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I87048295"]},{"raw_affiliation_string":"Linguamatics Ltd, 324 Cambridge Science Park, Milton Road, Cambridge, CB4 0WG, UK","institution_ids":["https://openalex.org/I4210103233"]},{"raw_affiliation_string":"European Bioinformatics Institute, Wellcome Trust Genome Campus, Hinxton, UK","institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I87048295"]},{"raw_affiliation_string":"Linguamatics Ltd, Cambridge, UK","institution_ids":["https://openalex.org/I4210103233"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5006224704"],"corresponding_institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I202697423","https://openalex.org/I87048295"],"apc_list":{"value":1190,"currency":"GBP","value_usd":1459},"apc_paid":{"value":1190,"currency":"GBP","value_usd":1459},"fwci":0.9629,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.75056191,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"4","issue":"1","first_page":"28","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.979200005531311,"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":0.979200005531311,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.006200000178068876,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.002899999963119626,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8270361423492432},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6765042543411255},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.666024923324585},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6205976009368896},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5651747584342957},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5414654016494751},{"id":"https://openalex.org/keywords/f1-score","display_name":"F1 score","score":0.5207933783531189},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.4804624915122986},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.452046662569046},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3730274438858032},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1398097574710846}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8270361423492432},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6765042543411255},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.666024923324585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6205976009368896},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5651747584342957},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5414654016494751},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.5207933783531189},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.4804624915122986},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.452046662569046},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3730274438858032},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1398097574710846},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1186/2041-1480-4-28","is_oa":true,"landing_page_url":"https://doi.org/10.1186/2041-1480-4-28","pdf_url":"https://jbiomedsem.biomedcentral.com/counter/pdf/10.1186/2041-1480-4-28","source":{"id":"https://openalex.org/S172276550","display_name":"Journal of Biomedical Semantics","issn_l":"2041-1480","issn":["2041-1480"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Biomedical Semantics","raw_type":"journal-article"},{"id":"pmid:24112383","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/24112383","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":"Journal of biomedical semantics","raw_type":null},{"id":"pmh:oai:www.zora.uzh.ch:82213","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401281","display_name":"Zurich Open Repository and Archive (University of Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I202697423","host_organization_name":"University of Zurich","host_organization_lineage":["https://openalex.org/I202697423"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Rebholz-Schuhmann, Dietrich; Kafkas, Senay; Kim, Jee-hyub; Li, Chen; Yepes, Antonio Jimeno; Hoehndorf, Robert; Backofen, Rolf; Lewin, Ian (2013). Evaluating gold standard corpora against gene/protein tagging solutions and lexical resources. Journal of Biomedical Semantics, 4:28.","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:jupiter.its.unimelb.edu.au:11343/263512","is_oa":true,"landing_page_url":"http://hdl.handle.net/11343/263512","pdf_url":"http://hdl.handle.net/11343/263512","source":{"id":"https://openalex.org/S4377196259","display_name":"Minerva Access (University of Melbourne)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I165779595","host_organization_name":"The University of Melbourne","host_organization_lineage":["https://openalex.org/I165779595"],"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":"Journal Article"},{"id":"pmh:oai:aber.ac.uk:publications/05606df5-6f93-43d5-b99f-8951e5b98b66","is_oa":false,"landing_page_url":"https://pure.aber.ac.uk/portal/en/publications/evaluating-gold-standard-corpora-against-geneprotein-tagging-solutions-and-lexical-resources(05606df5-6f93-43d5-b99f-8951e5b98b66).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306401660","display_name":"Aberystwyth Research portal (Aberystwyth University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I16038530","host_organization_name":"Aberystwyth University","host_organization_lineage":["https://openalex.org/I16038530"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:europepmc.org:3008586","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4021975","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":null,"raw_type":"Text"},{"id":"doi:10.5167/uzh-82213","is_oa":true,"landing_page_url":"https://doi.org/10.5167/uzh-82213","pdf_url":null,"source":{"id":"https://openalex.org/S7407051291","display_name":"Universit\u00e4t Z\u00fcrich, ZORA","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"JournalArticle"}],"best_oa_location":{"id":"doi:10.1186/2041-1480-4-28","is_oa":true,"landing_page_url":"https://doi.org/10.1186/2041-1480-4-28","pdf_url":"https://jbiomedsem.biomedcentral.com/counter/pdf/10.1186/2041-1480-4-28","source":{"id":"https://openalex.org/S172276550","display_name":"Journal of Biomedical Semantics","issn_l":"2041-1480","issn":["2041-1480"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Biomedical Semantics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310369","display_name":"National ICT Australia","ror":"https://ror.org/03q397159"},{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2139067830.pdf","grobid_xml":"https://content.openalex.org/works/W2139067830.grobid-xml"},"referenced_works_count":70,"referenced_works":["https://openalex.org/W61219374","https://openalex.org/W137651377","https://openalex.org/W239119325","https://openalex.org/W1529842856","https://openalex.org/W1578955001","https://openalex.org/W1592053870","https://openalex.org/W1959755538","https://openalex.org/W1973646872","https://openalex.org/W1976097579","https://openalex.org/W1979225493","https://openalex.org/W1994843778","https://openalex.org/W2005058680","https://openalex.org/W2007367068","https://openalex.org/W2009341227","https://openalex.org/W2024159593","https://openalex.org/W2030390110","https://openalex.org/W2032445314","https://openalex.org/W2033237963","https://openalex.org/W2039612385","https://openalex.org/W2040298461","https://openalex.org/W2042711932","https://openalex.org/W2044420612","https://openalex.org/W2045016337","https://openalex.org/W2048140075","https://openalex.org/W2050902903","https://openalex.org/W2054558802","https://openalex.org/W2070127972","https://openalex.org/W2074640468","https://openalex.org/W2094591616","https://openalex.org/W2094726706","https://openalex.org/W2097678794","https://openalex.org/W2101265630","https://openalex.org/W2107005506","https://openalex.org/W2107580398","https://openalex.org/W2108010925","https://openalex.org/W2109487646","https://openalex.org/W2112671334","https://openalex.org/W2114361266","https://openalex.org/W2116159459","https://openalex.org/W2117479478","https://openalex.org/W2117770626","https://openalex.org/W2122545791","https://openalex.org/W2123439964","https://openalex.org/W2126276057","https://openalex.org/W2127603354","https://openalex.org/W2127869678","https://openalex.org/W2129113459","https://openalex.org/W2130260860","https://openalex.org/W2141869602","https://openalex.org/W2142364412","https://openalex.org/W2142741334","https://openalex.org/W2144896636","https://openalex.org/W2144949988","https://openalex.org/W2150252713","https://openalex.org/W2154139219","https://openalex.org/W2154142897","https://openalex.org/W2155461328","https://openalex.org/W2155832627","https://openalex.org/W2156111363","https://openalex.org/W2157870551","https://openalex.org/W2159335058","https://openalex.org/W2159620792","https://openalex.org/W2162461580","https://openalex.org/W2162965868","https://openalex.org/W2163107094","https://openalex.org/W2168091548","https://openalex.org/W2169918010","https://openalex.org/W2263893547","https://openalex.org/W4237381349","https://openalex.org/W4240578612"],"related_works":["https://openalex.org/W2358294942","https://openalex.org/W4367460280","https://openalex.org/W4328049145","https://openalex.org/W4387490204","https://openalex.org/W3212239346","https://openalex.org/W4389848424","https://openalex.org/W4386414453","https://openalex.org/W4388937883","https://openalex.org/W4385625287","https://openalex.org/W4293205612"],"abstract_inverted_index":{"MOTIVATION:":[0],"The":[1,179,219,301,326,369,390],"identification":[2,60],"of":[3,61,65,70,74,112,136,257,353,392],"protein":[4],"and":[5,17,28,40,50,57,67,82,108,156,177,184,193,248,313,335,346,410],"gene":[6],"names":[7],"(PGNs)":[8],"from":[9,230,291],"the":[10,21,29,53,62,75,110,113,124,134,154,162,187,197,226,231,235,240,245,251,255,258,263,354,363,367,379,393,403,413],"scientific":[11],"literature":[12],"requires":[13],"semantic":[14],"resources:":[15],"Terminological":[16],"lexical":[18,115,209,400],"resources":[19,93,401],"deliver":[20],"term":[22,38,364],"candidates":[23],"into":[24],"PGN":[25,102,147],"tagging":[26,148,264,404],"solutions":[27,181,189,221,267,304,328,376,405],"gold":[30],"standard":[31,81,302],"corpora":[32,107,247,321],"(GSC)":[33],"train":[34],"them":[35],"to":[36,133,297,322,374],"identify":[37],"parameters":[39],"contextual":[41],"features.":[42],"Ideally":[43],"all":[44,69,201,311],"three":[45,76,92],"resources,":[46,210],"i.e.":[47],"corpora,":[48,312],"lexica":[49],"taggers,":[51],"cover":[52,68,350],"same":[54,63,198,232],"domain":[55],"knowledge,":[56],"thus":[58,314],"support":[59],"types":[64],"PGNs":[66],"them.":[71],"Unfortunately,":[72],"none":[73],"serves":[77],"as":[78,234],"a":[79,272,292,351,416],"predominant":[80],"for":[83,146,332,415],"this":[84],"reason":[85],"it":[86],"is":[87,205,229,344],"worth":[88],"exploring,":[89],"how":[90],"these":[91],"comply":[94],"with":[95,169,207,278,339,362,398],"each":[96],"other.":[97],"We":[98],"systematically":[99],"compare":[100],"different":[101,191,320,330],"taggers":[103],"against":[104,153],"publicly":[105],"available":[106],"analyze":[109],"impact":[111],"included":[114],"resource":[116,275],"in":[117,167,276,286,295,396,402],"their":[118,333,383,388,408],"performance.":[119],"In":[120,140],"particular,":[121],"we":[122],"determine":[123],"performance":[125,152],"gains":[126],"through":[127],"false":[128,241,259,279,370],"positive":[129,217,260,280,371],"filtering,":[130],"which":[131,211],"contributes":[132],"disambiguation":[135,170],"identified":[137],"PGNs.":[138],"RESULTS:":[139],"general,":[141],"machine":[142],"learning":[143],"approaches":[144,165],"(ML-Tag)":[145],"show":[149,172],"higher":[150],"F1-measure":[151,199],"BioCreative-II":[155],"Jnlpba":[157],"GSCs":[158],"(exact":[159],"matching),":[160],"whereas":[161,186],"lexicon":[163],"based":[164,270],"(LexTag)":[166],"combination":[168,277,397],"methods":[171],"better":[173,283],"results":[174,380],"on":[175,250,271],"FsuPrge":[176],"PennBio.":[178],"ML-Tag":[180,220,298,303],"balance":[182],"precision":[183,192,334,384],"recall,":[185],"LexTag":[188,327,375],"have":[190,329],"recall":[194,204,336],"profiles":[195,256,331],"at":[196],"across":[200,310,366],"corpora.":[202,368],"Higher":[203],"achieved":[206],"larger":[208],"also":[212],"introduce":[213],"more":[214],"noise":[215],"(false":[216],"results).":[218],"certainly":[222],"perform":[223],"best,":[224],"if":[225],"test":[227,246],"corpus":[228],"GSC":[233],"training":[236],"corpus.":[237],"As":[238],"expected,":[239],"negative":[242],"errors":[243],"characterize":[244,262],"-":[249,254],"other":[252],"hand":[253],"mistakes":[261],"solutions.":[265,299],"Lex-Tag":[266],"that":[268,348],"are":[269],"large":[273],"terminological":[274],"filtering":[281,372],"produce":[282],"results,":[284],"which,":[285],"addition,":[287],"provide":[288],"concept":[289],"identifiers":[290],"knowledge":[293],"source":[294],"contrast":[296],"CONCLUSION:":[300],"achieve":[305],"high":[306],"performance,":[307,337],"but":[308,338,359],"not":[309],"should":[315],"be":[316],"trained":[317],"using":[318],"several":[319],"reduce":[323],"possible":[324],"biases.":[325],"similar":[340],"F1-measure.":[341],"This":[342],"result":[343],"surprising":[345],"suggests":[347],"they":[349],"portion":[352],"most":[355],"common":[356],"naming":[357],"standards,":[358],"cope":[360],"differently":[361],"variability":[365],"applied":[373],"does":[377],"improve":[378],"by":[381],"increasing":[382],"without":[385],"compromising":[386],"significantly":[387],"recall.":[389],"harmonisation":[391],"annotation":[394],"schemes":[395],"standardized":[399],"will":[406,411],"enable":[407],"comparability":[409],"pave":[412],"way":[414],"shared":[417],"standard.":[418]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}