{"id":"https://openalex.org/W2055032581","doi":"https://doi.org/10.1186/1471-2105-13-207","title":"A corpus of full-text journal articles is a robust evaluation tool for revealing differences in performance of biomedical natural language processing tools","display_name":"A corpus of full-text journal articles is a robust evaluation tool for revealing differences in performance of biomedical natural language processing tools","publication_year":2012,"publication_date":"2012-08-17","ids":{"openalex":"https://openalex.org/W2055032581","doi":"https://doi.org/10.1186/1471-2105-13-207","mag":"2055032581","pmid":"https://pubmed.ncbi.nlm.nih.gov/22901054"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-13-207","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-13-207","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-13-207","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"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":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-13-207","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5067214173","display_name":"Karin Verspoor","orcid":"https://orcid.org/0000-0002-8661-1544"},"institutions":[{"id":"https://openalex.org/I921990950","display_name":"University of Colorado Denver","ror":"https://ror.org/02hh7en24","country_code":"US","type":"education","lineage":["https://openalex.org/I921990950"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Karin Verspoor","raw_affiliation_strings":["Computational Bioscience Program, U, Colorado School of Medicine, 12801 E 17th Ave, Aurora, MS 8303, CO 80045, USA. karin.verspoor@ucdenver.edu","Computational Bioscience Program, U. Colorado School of Medicine, 12801 E 17th Ave, Aurora, MS 8303, CO, 80045, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Bioscience Program, U, Colorado School of Medicine, 12801 E 17th Ave, Aurora, MS 8303, CO 80045, USA. karin.verspoor@ucdenver.edu","institution_ids":["https://openalex.org/I921990950"]},{"raw_affiliation_string":"Computational Bioscience Program, U. Colorado School of Medicine, 12801 E 17th Ave, Aurora, MS 8303, CO, 80045, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062221063","display_name":"Kevin Bretonnel Cohen","orcid":"https://orcid.org/0000-0003-1749-8290"},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Bretonnel Cohen","raw_affiliation_strings":["Computational Bioscience Program, U. Colorado School of Medicine, 12801 E 17th Ave, Aurora, MS 8303, CO, 80045, USA","Department of Linguistics, University of Colorado Boulder, Boulder, 290 Hellems, CO, 80309, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Bioscience Program, U. Colorado School of Medicine, 12801 E 17th Ave, Aurora, MS 8303, CO, 80045, USA","institution_ids":[]},{"raw_affiliation_string":"Department of Linguistics, University of Colorado Boulder, Boulder, 290 Hellems, CO, 80309, USA","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022600328","display_name":"Arrick Lanfranchi","orcid":null},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arrick Lanfranchi","raw_affiliation_strings":["Department of Linguistics, University of Colorado Boulder, Boulder, 290 Hellems, CO, 80309, USA","Institute of Cognitive Science, University of Colorado Boulder, Boulder, MUEN PSYCH Building D414, CO, 80309, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Linguistics, University of Colorado Boulder, Boulder, 290 Hellems, CO, 80309, USA","institution_ids":["https://openalex.org/I188538660"]},{"raw_affiliation_string":"Institute of Cognitive Science, University of Colorado Boulder, Boulder, MUEN PSYCH Building D414, CO, 80309, USA","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083530830","display_name":"Colin Warner","orcid":null},"institutions":[{"id":"https://openalex.org/I6902469","display_name":"Brandeis University","ror":"https://ror.org/05abbep66","country_code":"US","type":"education","lineage":["https://openalex.org/I6902469"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Colin Warner","raw_affiliation_strings":["Department of Computer Science, Brandeis University, Waltham, MS 018, MA, 02454, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Brandeis University, Waltham, MS 018, MA, 02454, USA","institution_ids":["https://openalex.org/I6902469"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017417252","display_name":"H. L. Johnson","orcid":"https://orcid.org/0000-0003-1873-2085"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Helen L Johnson","raw_affiliation_strings":["Computational Bioscience Program, U. Colorado School of Medicine, 12801 E 17th Ave, Aurora, MS 8303, CO, 80045, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Bioscience Program, U. Colorado School of Medicine, 12801 E 17th Ave, Aurora, MS 8303, CO, 80045, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008626087","display_name":"Christophe Roeder","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christophe Roeder","raw_affiliation_strings":["Computational Bioscience Program, U. Colorado School of Medicine, 12801 E 17th Ave, Aurora, MS 8303, CO, 80045, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Bioscience Program, U. Colorado School of Medicine, 12801 E 17th Ave, Aurora, MS 8303, CO, 80045, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104310998","display_name":"Jinho D. Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinho D Choi","raw_affiliation_strings":["Institute of Cognitive Science, University of Colorado Boulder, Boulder, MUEN PSYCH Building D414, CO, 80309, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Cognitive Science, University of Colorado Boulder, Boulder, MUEN PSYCH Building D414, CO, 80309, USA","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033755985","display_name":"Christopher Funk","orcid":"https://orcid.org/0000-0001-6613-7374"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christopher Funk","raw_affiliation_strings":["Computational Bioscience Program, U. Colorado School of Medicine, 12801 E 17th Ave, Aurora, MS 8303, CO, 80045, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Bioscience Program, U. Colorado School of Medicine, 12801 E 17th Ave, Aurora, MS 8303, CO, 80045, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043209435","display_name":"Yuriy Malenkiy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuriy Malenkiy","raw_affiliation_strings":["Computational Bioscience Program, U. Colorado School of Medicine, 12801 E 17th Ave, Aurora, MS 8303, CO, 80045, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Bioscience Program, U. Colorado School of Medicine, 12801 E 17th Ave, Aurora, MS 8303, CO, 80045, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109167532","display_name":"Miriam Eckert","orcid":null},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miriam Eckert","raw_affiliation_strings":["Department of Linguistics, University of Colorado Boulder, Boulder, 290 Hellems, CO, 80309, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Linguistics, University of Colorado Boulder, Boulder, 290 Hellems, CO, 80309, USA","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036715761","display_name":"Nianwen Xue","orcid":"https://orcid.org/0000-0002-4364-3618"},"institutions":[{"id":"https://openalex.org/I6902469","display_name":"Brandeis University","ror":"https://ror.org/05abbep66","country_code":"US","type":"education","lineage":["https://openalex.org/I6902469"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nianwen Xue","raw_affiliation_strings":["Department of Computer Science, Brandeis University, Waltham, MS 018, MA, 02454, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Brandeis University, Waltham, MS 018, MA, 02454, USA","institution_ids":["https://openalex.org/I6902469"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111881812","display_name":"William A. Baumgartner","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"William A Baumgartner","raw_affiliation_strings":["Computational Bioscience Program, U. Colorado School of Medicine, 12801 E 17th Ave, Aurora, MS 8303, CO, 80045, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Bioscience Program, U. Colorado School of Medicine, 12801 E 17th Ave, Aurora, MS 8303, CO, 80045, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083125835","display_name":"Michael Bada","orcid":"https://orcid.org/0000-0003-3366-4738"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Bada","raw_affiliation_strings":["Computational Bioscience Program, U. Colorado School of Medicine, 12801 E 17th Ave, Aurora, MS 8303, CO, 80045, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Bioscience Program, U. Colorado School of Medicine, 12801 E 17th Ave, Aurora, MS 8303, CO, 80045, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017464054","display_name":"Martha Palmer","orcid":"https://orcid.org/0000-0001-9864-6974"},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martha Palmer","raw_affiliation_strings":["Department of Linguistics, University of Colorado Boulder, Boulder, 290 Hellems, CO, 80309, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Linguistics, University of Colorado Boulder, Boulder, 290 Hellems, CO, 80309, USA","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041860080","display_name":"Lawrence Hunter","orcid":"https://orcid.org/0000-0003-1455-3370"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lawrence E Hunter","raw_affiliation_strings":["Computational Bioscience Program, U. Colorado School of Medicine, 12801 E 17th Ave, Aurora, MS 8303, CO, 80045, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Bioscience Program, U. Colorado School of Medicine, 12801 E 17th Ave, Aurora, MS 8303, CO, 80045, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":15,"corresponding_author_ids":["https://openalex.org/A5067214173"],"corresponding_institution_ids":["https://openalex.org/I921990950"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":7.6589,"has_fulltext":true,"cited_by_count":144,"citation_normalized_percentile":{"value":0.98208369,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"13","issue":"1","first_page":"207","last_page":"207"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.7530999779701233,"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":0.7530999779701233,"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":0.10849999636411667,"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/T13629","display_name":"Text Readability and Simplification","score":0.035599999129772186,"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":0.6385592818260193},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5892947316169739},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.48994535207748413},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4236080050468445},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40627017617225647},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3737010359764099},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.17925316095352173}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6385592818260193},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5892947316169739},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.48994535207748413},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4236080050468445},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40627017617225647},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3737010359764099},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.17925316095352173},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[{"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":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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:10.1186/1471-2105-13-207","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-13-207","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-13-207","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"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":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:22901054","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/22901054","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:jupiter.its.unimelb.edu.au:11343/263195","is_oa":true,"landing_page_url":"http://hdl.handle.net/11343/263195","pdf_url":"http://hdl.handle.net/11343/263195","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"},{"id":"pmh:oai:doaj.org/article:f3f09127c23d466eb15a62f73ef42e42","is_oa":false,"landing_page_url":"https://doaj.org/article/f3f09127c23d466eb15a62f73ef42e42","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 13, Iss 1, p 207 (2012)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:2487364","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3483229","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"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-13-207","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-13-207","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-13-207","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"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":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G178714339","display_name":null,"funder_award_id":"R01LM008111","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G2675965548","display_name":null,"funder_award_id":"RR025780","funder_id":"https://openalex.org/F4320337375","funder_display_name":"National Center for Research Resources"},{"id":"https://openalex.org/G3945006501","display_name":null,"funder_award_id":"R01LM009254","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G5430415865","display_name":null,"funder_award_id":"UL1 RR025780","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G5994683803","display_name":null,"funder_award_id":"RR025780","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6986171645","display_name":null,"funder_award_id":"UL1 RR025780","funder_id":"https://openalex.org/F4320337375","funder_display_name":"National Center for Research Resources"},{"id":"https://openalex.org/G8331699053","display_name":null,"funder_award_id":"Grant Number UL1 RR025780","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337375","display_name":"National Center for Research Resources","ror":"https://ror.org/04pw6fb54"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2055032581.pdf","grobid_xml":"https://content.openalex.org/works/W2055032581.grobid-xml"},"referenced_works_count":75,"referenced_works":["https://openalex.org/W58522540","https://openalex.org/W76749362","https://openalex.org/W108101778","https://openalex.org/W122290181","https://openalex.org/W199456390","https://openalex.org/W900993354","https://openalex.org/W1502957213","https://openalex.org/W1524281572","https://openalex.org/W1558788122","https://openalex.org/W1570795998","https://openalex.org/W1607035479","https://openalex.org/W1632114991","https://openalex.org/W1648311451","https://openalex.org/W1741471566","https://openalex.org/W1817582244","https://openalex.org/W1818857488","https://openalex.org/W1849985792","https://openalex.org/W1850865022","https://openalex.org/W1942234578","https://openalex.org/W1968848598","https://openalex.org/W2001804590","https://openalex.org/W2018874418","https://openalex.org/W2032566933","https://openalex.org/W2040298461","https://openalex.org/W2043335066","https://openalex.org/W2047782770","https://openalex.org/W2048140075","https://openalex.org/W2056569219","https://openalex.org/W2066053858","https://openalex.org/W2068017609","https://openalex.org/W2071993998","https://openalex.org/W2075322787","https://openalex.org/W2092419931","https://openalex.org/W2096525273","https://openalex.org/W2097898123","https://openalex.org/W2103470346","https://openalex.org/W2107005506","https://openalex.org/W2107580398","https://openalex.org/W2107879810","https://openalex.org/W2122228338","https://openalex.org/W2122904379","https://openalex.org/W2122922578","https://openalex.org/W2123171788","https://openalex.org/W2129113459","https://openalex.org/W2131395877","https://openalex.org/W2132288458","https://openalex.org/W2137881949","https://openalex.org/W2139621418","https://openalex.org/W2141274067","https://openalex.org/W2143078730","https://openalex.org/W2144001613","https://openalex.org/W2148564836","https://openalex.org/W2153274216","https://openalex.org/W2154142897","https://openalex.org/W2154333659","https://openalex.org/W2158505321","https://openalex.org/W2163107094","https://openalex.org/W2163568299","https://openalex.org/W2167072947","https://openalex.org/W2169918010","https://openalex.org/W2251569341","https://openalex.org/W2480294864","https://openalex.org/W2524645877","https://openalex.org/W2531621976","https://openalex.org/W2617702020","https://openalex.org/W2891636418","https://openalex.org/W2893578842","https://openalex.org/W2912409473","https://openalex.org/W2914431807","https://openalex.org/W3083577572","https://openalex.org/W4244606935","https://openalex.org/W4250498225","https://openalex.org/W4250552034","https://openalex.org/W4285719527","https://openalex.org/W4300022934"],"related_works":["https://openalex.org/W4283262748","https://openalex.org/W2502773048","https://openalex.org/W1979668694","https://openalex.org/W48866389","https://openalex.org/W2117651364","https://openalex.org/W3112533414","https://openalex.org/W2490481324","https://openalex.org/W4312662746","https://openalex.org/W2364036969","https://openalex.org/W3204019825"],"abstract_inverted_index":{"BACKGROUND:":[0],"We":[1,24],"introduce":[2],"the":[3,16,27,65,71,119,122,152,166],"linguistic":[4],"annotation":[5],"of":[6,9,29,121,131,176],"a":[7,162],"corpus":[8,67,110,124,160],"97":[10],"full-text":[11,155],"biomedical":[12,48,167,180],"publications,":[13],"known":[14],"as":[15],"Colorado":[17],"Richly":[18],"Annotated":[19],"Full":[20],"Text":[21],"(CRAFT)":[22],"corpus.":[23,45],"further":[25],"assess":[26],"performance":[28,63,130],"existing":[30],"tools":[31],"for":[32,172,179],"performing":[33],"sentence":[34],"splitting,":[35],"tokenization,":[36],"syntactic":[37],"parsing,":[38],"and":[39,61,174],"named":[40],"entity":[41],"recognition":[42],"on":[43,64,92,108],"this":[44,93,109],"RESULTS:":[46],"Many":[47],"natural":[49,144,168],"language":[50,145,169],"processing":[51,146,170],"systems":[52,79,100,133,147],"demonstrated":[53],"large":[54],"differences":[55],"between":[56],"their":[57,62,85],"previously":[58],"published":[59],"results":[60],"CRAFT":[66,123,159],"when":[68,151],"tested":[69],"with":[70,82],"publicly":[72],"available":[73],"models":[74,90,106,178],"or":[75],"rule":[76],"sets.":[77],"Trainable":[78],"differed":[80],"widely":[81],"respect":[83],"to":[84,87,103,139,142,148,165],"ability":[86],"build":[88],"high-performing":[89,105],"based":[91,107],"data.":[94],"CONCLUSIONS:":[95],"The":[96,127,158],"finding":[97],"that":[98,118,135],"some":[99],"were":[101],"able":[102],"train":[104],"is":[111,125,154],"additional":[112],"evidence,":[113],"beyond":[114],"high":[115],"inter-annotator":[116],"agreement,":[117],"quality":[120],"high.":[126],"overall":[128],"poor":[129],"various":[132],"indicates":[134],"considerable":[136],"work":[137,149],"needs":[138],"be":[140],"done":[141],"enable":[143],"well":[150],"input":[153],"journal":[156],"articles.":[157],"provides":[161],"valuable":[163],"resource":[164],"community":[171],"evaluation":[173],"training":[175],"new":[177],"full":[181],"text":[182],"publications.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":17},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":26},{"year":2013,"cited_by_count":14},{"year":2012,"cited_by_count":8}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}
