{"id":"https://openalex.org/W2043309298","doi":"https://doi.org/10.1186/s12859-015-0539-7","title":"Feature engineering for MEDLINE citation categorization with MeSH","display_name":"Feature engineering for MEDLINE citation categorization with MeSH","publication_year":2015,"publication_date":"2015-04-07","ids":{"openalex":"https://openalex.org/W2043309298","doi":"https://doi.org/10.1186/s12859-015-0539-7","mag":"2043309298","pmid":"https://pubmed.ncbi.nlm.nih.gov/25887792"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-015-0539-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-015-0539-7","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-015-0539-7","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/s12859-015-0539-7","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077681143","display_name":"Antonio Jimeno Yepes","orcid":"https://orcid.org/0000-0002-6581-094X"},"institutions":[{"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/I2800548410","display_name":"United States National Library of Medicine","ror":"https://ror.org/0060t0j89","country_code":"US","type":"archive","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410"]}],"countries":["AU","US"],"is_corresponding":true,"raw_author_name":"Antonio Jose Jimeno Yepes","raw_affiliation_strings":["Department of Computing and Information Systems, The University of Melbourne, Parkville, 3010, VIC, Australia. antonio.jimeno@gmail.com","National Library of Medicine, 8600 Rockville Pike, Bethesda, MD 20894, USA. antonio.jimeno@gmail.com","Department of Computing and Information Systems, The University of Melbourne, Parkville, Australia","National Library of Medicine, Bethesda, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing and Information Systems, The University of Melbourne, Parkville, 3010, VIC, Australia. antonio.jimeno@gmail.com","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"National Library of Medicine, 8600 Rockville Pike, Bethesda, MD 20894, USA. antonio.jimeno@gmail.com","institution_ids":["https://openalex.org/I2800548410"]},{"raw_affiliation_string":"Department of Computing and Information Systems, The University of Melbourne, Parkville, Australia","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"National Library of Medicine, Bethesda, USA","institution_ids":["https://openalex.org/I2800548410"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057033593","display_name":"Laura Plaza","orcid":"https://orcid.org/0000-0001-5144-8014"},"institutions":[{"id":"https://openalex.org/I178450904","display_name":"Universidad Nacional de Educaci\u00f3n a Distancia","ror":"https://ror.org/02msb5n36","country_code":"ES","type":"education","lineage":["https://openalex.org/I178450904"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Laura Plaza","raw_affiliation_strings":["UNED NLP & IR Group, C/Juan del Rosal 16, Madrid, 28040, Spain. lplaza@lsi.uned.es","UNED NLP and IR Group, Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UNED NLP & IR Group, C/Juan del Rosal 16, Madrid, 28040, Spain. lplaza@lsi.uned.es","institution_ids":["https://openalex.org/I178450904"]},{"raw_affiliation_string":"UNED NLP and IR Group, Madrid, Spain","institution_ids":["https://openalex.org/I178450904"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039395334","display_name":"Jorge Carrillo\u2010de\u2010Albornoz","orcid":"https://orcid.org/0000-0002-1449-1547"},"institutions":[{"id":"https://openalex.org/I178450904","display_name":"Universidad Nacional de Educaci\u00f3n a Distancia","ror":"https://ror.org/02msb5n36","country_code":"ES","type":"education","lineage":["https://openalex.org/I178450904"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jorge Carrillo-de-Albornoz","raw_affiliation_strings":["UNED NLP & IR Group, C/Juan del Rosal 16, Madrid, 28040, Spain. jcalbornoz@lsi.uned.es","UNED NLP and IR Group, Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UNED NLP & IR Group, C/Juan del Rosal 16, Madrid, 28040, Spain. jcalbornoz@lsi.uned.es","institution_ids":["https://openalex.org/I178450904"]},{"raw_affiliation_string":"UNED NLP and IR Group, Madrid, Spain","institution_ids":["https://openalex.org/I178450904"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022152853","display_name":"James G. Mork","orcid":"https://orcid.org/0000-0002-0346-1350"},"institutions":[{"id":"https://openalex.org/I2800548410","display_name":"United States National Library of Medicine","ror":"https://ror.org/0060t0j89","country_code":"US","type":"archive","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James G Mork","raw_affiliation_strings":["National Library of Medicine, 8600 Rockville Pike, Bethesda, MD 20894, USA. mork@nlm.nih.gov","[National Library of Medicine, Bethesda, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Library of Medicine, 8600 Rockville Pike, Bethesda, MD 20894, USA. mork@nlm.nih.gov","institution_ids":["https://openalex.org/I2800548410"]},{"raw_affiliation_string":"[National Library of Medicine, Bethesda, USA]","institution_ids":["https://openalex.org/I2800548410"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018615989","display_name":"Alan R. Aronson","orcid":null},"institutions":[{"id":"https://openalex.org/I2800548410","display_name":"United States National Library of Medicine","ror":"https://ror.org/0060t0j89","country_code":"US","type":"archive","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alan R Aronson","raw_affiliation_strings":["National Library of Medicine, 8600 Rockville Pike, Bethesda, MD 20894, USA. alan@nlm.nih.gov","[National Library of Medicine, Bethesda, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Library of Medicine, 8600 Rockville Pike, Bethesda, MD 20894, USA. alan@nlm.nih.gov","institution_ids":["https://openalex.org/I2800548410"]},{"raw_affiliation_string":"[National Library of Medicine, Bethesda, USA]","institution_ids":["https://openalex.org/I2800548410"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5077681143"],"corresponding_institution_ids":["https://openalex.org/I165779595","https://openalex.org/I2800548410"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":1.9285,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":{"value":0.85922675,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":"16","issue":"1","first_page":"113","last_page":"113"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.8062000274658203,"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":0.8062000274658203,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.09849999845027924,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.017799999564886093,"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/categorization","display_name":"Categorization","score":0.824069082736969},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6591446399688721},{"id":"https://openalex.org/keywords/citation","display_name":"Citation","score":0.5958848595619202},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5817950963973999},{"id":"https://openalex.org/keywords/medline","display_name":"MEDLINE","score":0.575115442276001},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.49455806612968445},{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.42055800557136536},{"id":"https://openalex.org/keywords/text-mining","display_name":"Text mining","score":0.41449007391929626},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.35297638177871704},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.33232375979423523},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3210603594779968},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2697603106498718},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2697139382362366},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.23097312450408936},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2220197319984436},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.0865069031715393},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06883406639099121}],"concepts":[{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.824069082736969},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6591446399688721},{"id":"https://openalex.org/C2778805511","wikidata":"https://www.wikidata.org/wiki/Q1713","display_name":"Citation","level":2,"score":0.5958848595619202},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5817950963973999},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.575115442276001},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49455806612968445},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.42055800557136536},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.41449007391929626},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35297638177871704},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.33232375979423523},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3210603594779968},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2697603106498718},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2697139382362366},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.23097312450408936},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2220197319984436},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0865069031715393},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06883406639099121},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0}],"mesh":[{"descriptor_ui":"D000043","descriptor_name":"Abstracting and Indexing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000043","descriptor_name":"Abstracting and Indexing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000043","descriptor_name":"Abstracting and Indexing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016239","descriptor_name":"MEDLINE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016239","descriptor_name":"MEDLINE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016239","descriptor_name":"MEDLINE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D046650","descriptor_name":"Medical Subject Headings","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D046650","descriptor_name":"Medical Subject Headings","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D046650","descriptor_name":"Medical Subject Headings","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-015-0539-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-015-0539-7","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-015-0539-7","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:25887792","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/25887792","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:11343/261535","is_oa":true,"landing_page_url":"http://hdl.handle.net/11343/261535","pdf_url":"http://hdl.handle.net/11343/261535","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:europepmc.org:3369517","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4407321","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/s12859-015-0539-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-015-0539-7","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/s12859-015-0539-7","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":[{"display_name":"Quality Education","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G8079601391","display_name":null,"funder_award_id":"TIN2010-21128-C02","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"},{"id":"https://openalex.org/G904141716","display_name":null,"funder_award_id":"TIN2010-21128-C02-01","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"}],"funders":[{"id":"https://openalex.org/F4320320974","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98"},{"id":"https://openalex.org/F4320322930","display_name":"Ministerio de Ciencia e Innovaci\u00f3n","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2043309298.pdf","grobid_xml":"https://content.openalex.org/works/W2043309298.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W74342042","https://openalex.org/W103965747","https://openalex.org/W1508182670","https://openalex.org/W1519796834","https://openalex.org/W1520963883","https://openalex.org/W1522930027","https://openalex.org/W1550258693","https://openalex.org/W1755193636","https://openalex.org/W1846766366","https://openalex.org/W1967200031","https://openalex.org/W2004761926","https://openalex.org/W2027788481","https://openalex.org/W2027875450","https://openalex.org/W2056190334","https://openalex.org/W2057803903","https://openalex.org/W2058982198","https://openalex.org/W2061172803","https://openalex.org/W2070771761","https://openalex.org/W2071664212","https://openalex.org/W2085575316","https://openalex.org/W2088339844","https://openalex.org/W2094934653","https://openalex.org/W2101747459","https://openalex.org/W2111221376","https://openalex.org/W2118020653","https://openalex.org/W2122402213","https://openalex.org/W2126502509","https://openalex.org/W2127241285","https://openalex.org/W2137239793","https://openalex.org/W2137363497","https://openalex.org/W2140336868","https://openalex.org/W2145003932","https://openalex.org/W2149684865","https://openalex.org/W2156005162","https://openalex.org/W2158780731","https://openalex.org/W2159583324","https://openalex.org/W2160171761","https://openalex.org/W2166339213","https://openalex.org/W2166706824","https://openalex.org/W2170339378","https://openalex.org/W2170654002","https://openalex.org/W2171575133","https://openalex.org/W2240218274","https://openalex.org/W2250530842","https://openalex.org/W2250639155","https://openalex.org/W2396059247","https://openalex.org/W2398645150","https://openalex.org/W2404713095","https://openalex.org/W2545410393","https://openalex.org/W4245322178","https://openalex.org/W4256565756","https://openalex.org/W6683709678"],"related_works":["https://openalex.org/W2165912799","https://openalex.org/W2735662278","https://openalex.org/W2382615723","https://openalex.org/W4311804456","https://openalex.org/W1987484445","https://openalex.org/W2623658258","https://openalex.org/W2047139419","https://openalex.org/W1562480646","https://openalex.org/W2050178430","https://openalex.org/W2140995597"],"abstract_inverted_index":{"BACKGROUND:":[0],"Research":[1],"in":[2,250],"biomedical":[3,41],"text":[4,17,38],"categorization":[5],"has":[6,247],"mostly":[7],"used":[8],"the":[9,34,47,53,77,124,138,144,155,171,179,227,230,238,241,251,255,285,303],"bag-of-words":[10,231],"representation.":[11,232],"Other":[12],"more":[13,118,189],"sophisticated":[14],"representations":[15,39],"of":[16,36,40,50,52,76,123,146,153,173,229,240,254,274,287,291,305],"based":[18],"on":[19],"syntactic,":[20],"semantic":[21,74],"and":[22,62,73,84,111,209,244,294],"argumentative":[23],"properties":[24],"have":[25,113,211,234],"been":[26],"less":[27],"studied.":[28],"In":[29,58,166],"this":[30,168],"paper,":[31],"we":[32,183],"evaluate":[33],"impact":[35],"different":[37],"texts":[42,125],"as":[43,207],"features":[44,65,81,156,205,295],"for":[45,296],"reproducing":[46],"MeSH":[48,56,176,298],"annotations":[49],"some":[51],"most":[54],"frequent":[55],"headings.":[57],"addition":[59],"to":[60,90,117,132,191,215,221,224,262,278,284],"unigrams":[61,83,208],"bigrams,":[63],"these":[64],"include":[66],"noun":[67],"phrases,":[68],"citation":[69,71,104],"meta-data,":[70],"structure,":[72],"annotation":[75,122],"citations.":[78],"RESULTS:":[79],"Traditional":[80],"like":[82],"bigrams":[85,210],"exhibit":[86],"strong":[87,212],"performance":[88,115,130,145,172,213,228,253,304],"compared":[89,116,131,214],"other":[91,216],"feature":[92,163,245],"sets.":[93],"Little":[94],"or":[95,103],"no":[96],"improvement":[97],"is":[98,219],"obtained":[99],"when":[100,269],"using":[101,147,258,270],"meta-data":[102],"structure.":[105],"Noun":[106],"phrases":[107],"are":[108,188],"too":[109],"sparse":[110],"thus":[112],"lower":[114],"traditional":[119,204],"features.":[120],"Conceptual":[121],"by":[126],"MetaMap":[127],"shows":[128],"similar":[129],"unigrams,":[133],"but":[134],"adding":[135],"concepts":[136],"from":[137],"UMLS":[139],"taxonomy":[140],"does":[141],"not":[142],"improve":[143,226],"only":[148],"mapped":[149],"concepts.":[150],"The":[151],"combination":[152,169,239],"all":[154],"performs":[157],"largely":[158,194,265],"better":[159,196],"than":[160],"any":[161],"individual":[162,297],"set":[164,273],"considered.":[165],"addition,":[167],"improves":[170,266],"a":[174,271],"state-of-the-art":[175],"indexer.":[177],"Concerning":[178],"machine":[180],"learning":[181,242,259,292],"algorithms,":[182],"find":[184],"that":[185,187,201,237],"those":[186],"resilient":[190,261],"class":[192,263],"imbalance":[193,264],"obtain":[195],"performance.":[197,267],"CONCLUSIONS:":[198],"We":[199,233],"conclude":[200],"even":[202],"though":[203],"such":[206],"features,":[217,275],"it":[218],"possible":[220],"combine":[222],"them":[223],"effectively":[225],"also":[235],"found":[236],"algorithm":[243],"sets":[246],"an":[248,306],"influence":[249],"overall":[252],"system.":[256,308],"Moreover,":[257],"algorithms":[260,282,293],"However,":[268],"large":[272],"consideration":[276],"needs":[277],"be":[279],"taken":[280],"with":[281],"due":[283],"risk":[286],"over-fitting.":[288],"Specific":[289],"combinations":[290],"headings":[299],"could":[300],"further":[301],"increase":[302],"indexing":[307]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}
