{"id":"https://openalex.org/W2890531203","doi":"https://doi.org/10.1093/database/bay096","title":"Wide-scope biomedical named entity recognition and normalization with CRFs, fuzzy matching and character level modeling","display_name":"Wide-scope biomedical named entity recognition and normalization with CRFs, fuzzy matching and character level modeling","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2890531203","doi":"https://doi.org/10.1093/database/bay096","mag":"2890531203","pmid":"https://pubmed.ncbi.nlm.nih.gov/30239666"},"language":"en","primary_location":{"id":"doi:10.1093/database/bay096","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/bay096","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/bay096/27329393/bay096.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/bay096/27329393/bay096.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000080545","display_name":"Suwisa Kaewphan","orcid":"https://orcid.org/0000-0001-8534-1215"},"institutions":[{"id":"https://openalex.org/I155660961","display_name":"University of Turku","ror":"https://ror.org/05vghhr25","country_code":"FI","type":"education","lineage":["https://openalex.org/I155660961"]},{"id":"https://openalex.org/I183173800","display_name":"Turku Centre for Computer Science","ror":"https://ror.org/00vy7ed73","country_code":"FI","type":"facility","lineage":["https://openalex.org/I130217899","https://openalex.org/I155660961","https://openalex.org/I183173800"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Suwisa Kaewphan","raw_affiliation_strings":["Department of Future Technologies, University of Turku, Turku, Finland","Turku Centre for Computer Science, Turku, Finland","University of Turku Graduate School, Turku, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Future Technologies, University of Turku, Turku, Finland","institution_ids":["https://openalex.org/I155660961"]},{"raw_affiliation_string":"Turku Centre for Computer Science, Turku, Finland","institution_ids":["https://openalex.org/I183173800"]},{"raw_affiliation_string":"University of Turku Graduate School, Turku, Finland","institution_ids":["https://openalex.org/I155660961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058939594","display_name":"Kai Hakala","orcid":"https://orcid.org/0000-0001-8943-7011"},"institutions":[{"id":"https://openalex.org/I155660961","display_name":"University of Turku","ror":"https://ror.org/05vghhr25","country_code":"FI","type":"education","lineage":["https://openalex.org/I155660961"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Kai Hakala","raw_affiliation_strings":["Department of Future Technologies, University of Turku, Turku, Finland","University of Turku Graduate School, Turku, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Future Technologies, University of Turku, Turku, Finland","institution_ids":["https://openalex.org/I155660961"]},{"raw_affiliation_string":"University of Turku Graduate School, Turku, Finland","institution_ids":["https://openalex.org/I155660961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032294150","display_name":"Niko Miekka","orcid":null},"institutions":[{"id":"https://openalex.org/I155660961","display_name":"University of Turku","ror":"https://ror.org/05vghhr25","country_code":"FI","type":"education","lineage":["https://openalex.org/I155660961"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Niko Miekka","raw_affiliation_strings":["Department of Future Technologies, University of Turku, Turku, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Future Technologies, University of Turku, Turku, Finland","institution_ids":["https://openalex.org/I155660961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105839982","display_name":"Tapio Salakoski","orcid":null},"institutions":[{"id":"https://openalex.org/I155660961","display_name":"University of Turku","ror":"https://ror.org/05vghhr25","country_code":"FI","type":"education","lineage":["https://openalex.org/I155660961"]},{"id":"https://openalex.org/I183173800","display_name":"Turku Centre for Computer Science","ror":"https://ror.org/00vy7ed73","country_code":"FI","type":"facility","lineage":["https://openalex.org/I130217899","https://openalex.org/I155660961","https://openalex.org/I183173800"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tapio Salakoski","raw_affiliation_strings":["Turku Centre for Computer Science, Turku, Finland","University of Turku Graduate School, Turku, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Turku Centre for Computer Science, Turku, Finland","institution_ids":["https://openalex.org/I183173800"]},{"raw_affiliation_string":"University of Turku Graduate School, Turku, Finland","institution_ids":["https://openalex.org/I155660961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019929457","display_name":"Filip Ginter","orcid":"https://orcid.org/0000-0002-5484-6103"},"institutions":[{"id":"https://openalex.org/I155660961","display_name":"University of Turku","ror":"https://ror.org/05vghhr25","country_code":"FI","type":"education","lineage":["https://openalex.org/I155660961"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Filip Ginter","raw_affiliation_strings":["Department of Future Technologies, University of Turku, Turku, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Future Technologies, University of Turku, Turku, Finland","institution_ids":["https://openalex.org/I155660961"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5000080545"],"corresponding_institution_ids":["https://openalex.org/I155660961","https://openalex.org/I183173800"],"apc_list":{"value":1415,"currency":"GBP","value_usd":1735},"apc_paid":{"value":1200,"currency":"EUR","value_usd":1294},"fwci":0.9022,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.73904161,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"2018","issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9876000285148621,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.9749000072479248,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/crfs","display_name":"CRFS","score":0.8936238288879395},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7821074724197388},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.7078468203544617},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6789714694023132},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6429147124290466},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6109293699264526},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.6105228662490845},{"id":"https://openalex.org/keywords/fuzzy-logic","display_name":"Fuzzy logic","score":0.5311537981033325},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4874756336212158},{"id":"https://openalex.org/keywords/character-recognition","display_name":"Character recognition","score":0.4515196979045868},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.4268842935562134},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.10938817262649536},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08218547701835632},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.0742306113243103},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06025511026382446}],"concepts":[{"id":"https://openalex.org/C2775953691","wikidata":"https://www.wikidata.org/wiki/Q5013874","display_name":"CRFS","level":3,"score":0.8936238288879395},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7821074724197388},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.7078468203544617},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6789714694023132},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6429147124290466},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6109293699264526},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.6105228662490845},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.5311537981033325},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4874756336212158},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.4515196979045868},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.4268842935562134},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.10938817262649536},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08218547701835632},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0742306113243103},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06025511026382446},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[{"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":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017143","descriptor_name":"Fuzzy Logic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017143","descriptor_name":"Fuzzy Logic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017143","descriptor_name":"Fuzzy Logic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017143","descriptor_name":"Fuzzy Logic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D058977","descriptor_name":"Molecular Sequence Annotation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/database/bay096","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/bay096","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/bay096/27329393/bay096.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},{"id":"pmid:30239666","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30239666","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":"Database : the journal of biological databases and curation","raw_type":null},{"id":"pmh:oai:europepmc.org:5099547","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6146133","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:10.1093/database/bay096","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/bay096","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/bay096/27329393/bay096.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2890531203.pdf","grobid_xml":"https://content.openalex.org/works/W2890531203.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W192665053","https://openalex.org/W1527927437","https://openalex.org/W1601495365","https://openalex.org/W1610821757","https://openalex.org/W1780088415","https://openalex.org/W2033377040","https://openalex.org/W2041614298","https://openalex.org/W2052250375","https://openalex.org/W2061167720","https://openalex.org/W2081227087","https://openalex.org/W2116034137","https://openalex.org/W2120754707","https://openalex.org/W2142678031","https://openalex.org/W2157870551","https://openalex.org/W2165372747","https://openalex.org/W2207474836","https://openalex.org/W2229453122","https://openalex.org/W2414378847","https://openalex.org/W2509884321","https://openalex.org/W2518463060","https://openalex.org/W2527896214","https://openalex.org/W2574163994","https://openalex.org/W2734608416","https://openalex.org/W2739999456","https://openalex.org/W2741379117","https://openalex.org/W2763990719","https://openalex.org/W2809129309","https://openalex.org/W2896179748","https://openalex.org/W2968573267","https://openalex.org/W4234862494","https://openalex.org/W6636556141","https://openalex.org/W6662590293","https://openalex.org/W6663746913","https://openalex.org/W6678359697","https://openalex.org/W6681351124","https://openalex.org/W6688358287","https://openalex.org/W6697154816","https://openalex.org/W6724881955","https://openalex.org/W6728098186","https://openalex.org/W6732291820","https://openalex.org/W6742368032"],"related_works":["https://openalex.org/W1964783010","https://openalex.org/W2061834489","https://openalex.org/W4250494529","https://openalex.org/W2399696375","https://openalex.org/W45206245","https://openalex.org/W2045347339","https://openalex.org/W2763026339","https://openalex.org/W3088215229","https://openalex.org/W182104056","https://openalex.org/W2166353137"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,7,105],"system":[3,35,58],"for":[4,119,128],"automatically":[5],"identifying":[6],"multitude":[8],"of":[9],"biomedical":[10],"entities":[11],"from":[12],"the":[13,24,40,53,61,86],"literature.":[14],"This":[15],"work":[16],"is":[17],"based":[18],"on":[19],"our":[20,34],"previous":[21],"efforts":[22],"in":[23,32,44,60,115],"BioCreative":[25],"VI:":[26],"Interactive":[27],"Bio-ID":[28],"Assignment":[29],"shared":[30,62],"task":[31,63],"which":[33,78],"demonstrated":[36],"state-of-the-art":[37],"performance":[38,82],"with":[39,104],"highest":[41],"achieved":[42],"results":[43,118],"named":[45,130],"entity":[46,121,131],"recognition.":[47],"In":[48],"this":[49],"paper":[50],"we":[51,91],"describe":[52],"original":[54],"conditional":[55],"random":[56],"field-based":[57],"used":[59,127],"as":[64,66],"well":[65],"experiments":[67],"conducted":[68],"since,":[69],"including":[70],"better":[71,106],"hyperparameter":[72],"tuning":[73],"and":[74,110,125,133],"character":[75,94],"level":[76],"modeling,":[77],"led":[79],"to":[80],"further":[81],"improvements.":[83],"For":[84],"normalizing":[85],"mentions":[87],"into":[88],"unique":[89],"identifiers":[90],"use":[92],"fuzzy":[93],"n-gram":[95],"matching.":[96],"The":[97],"normalization":[98,134],"approach":[99],"has":[100],"also":[101],"been":[102],"improved":[103,117],"abbreviation":[107],"resolution":[108],"method":[109],"stricter":[111],"guideline":[112],"compliance":[113],"resulting":[114],"vastly":[116],"various":[120],"types.":[122],"All":[123],"tools":[124],"models":[126],"both":[129],"recognition":[132],"are":[135],"publicly":[136],"available":[137],"under":[138],"open":[139],"license.Database":[140],"URL:":[141],"https://github.com/TurkuNLP/BioCreativeVI_BioID_assignment.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
