{"id":"https://openalex.org/W2159640576","doi":"https://doi.org/10.1186/1471-2105-7-s5-s11","title":"NERBio: using selected word conjunctions, term normalization, and global patterns to improve biomedical named entity recognition","display_name":"NERBio: using selected word conjunctions, term normalization, and global patterns to improve biomedical named entity recognition","publication_year":2006,"publication_date":"2006-12-01","ids":{"openalex":"https://openalex.org/W2159640576","doi":"https://doi.org/10.1186/1471-2105-7-s5-s11","mag":"2159640576","pmid":"https://pubmed.ncbi.nlm.nih.gov/17254295"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-7-s5-s11","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-7-s5-s11","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-7-S5-S11","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/10.1186/1471-2105-7-S5-S11","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030771512","display_name":"Richard Tzong\u2010Han Tsai","orcid":"https://orcid.org/0000-0003-0513-107X"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Richard Tzong-Han Tsai","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Nankang, Taipei 115, Taiwan, Republic of China. thtsai@iis.sinica.edu.tw","Institute of Information Science, Academia Sinica, Nankang, Taipei 115, Taiwan, Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Nankang, Taipei 115, Taiwan, Republic of China. thtsai@iis.sinica.edu.tw","institution_ids":["https://openalex.org/I4210098366"]},{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Nankang, Taipei 115, Taiwan, Republic of China","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032523770","display_name":"Cheng-Lung Sung","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Cheng-Lung Sung","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Nankang, Taipei 115, Taiwan, Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Nankang, Taipei 115, Taiwan, Republic of China","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037362113","display_name":"Hong-Jie Dai","orcid":"https://orcid.org/0000-0002-1516-7255"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hong-Jie Dai","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Nankang, Taipei 115, Taiwan, Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Nankang, Taipei 115, Taiwan, Republic of China","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111940306","display_name":"Hsieh-Chuan Hung","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsieh-Chuan Hung","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Nankang, Taipei 115, Taiwan, Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Nankang, Taipei 115, Taiwan, Republic of China","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110550270","display_name":"Ting-Yi Sung","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ting-Yi Sung","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Nankang, Taipei 115, Taiwan, Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Nankang, Taipei 115, Taiwan, Republic of China","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112054430","display_name":"Wen-Lian Hsu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Wen-Lian Hsu","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Nankang, Taipei 115, Taiwan, Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Nankang, Taipei 115, Taiwan, Republic of China","institution_ids":["https://openalex.org/I4210098366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":3.9548,"has_fulltext":true,"cited_by_count":128,"citation_normalized_percentile":{"value":0.94203108,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"7","issue":"S5","first_page":"S11","last_page":"S11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9610000252723694,"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":0.9610000252723694,"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":0.023399999365210533,"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":0.002899999963119626,"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/named-entity-recognition","display_name":"Named-entity recognition","score":0.79129958152771},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7354726791381836},{"id":"https://openalex.org/keywords/numeral-system","display_name":"Numeral system","score":0.7297345995903015},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5568650960922241},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5503572225570679},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5414746403694153},{"id":"https://openalex.org/keywords/conjunction","display_name":"Conjunction (astronomy)","score":0.5411050319671631},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5157957077026367},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4454890191555023},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4292517900466919},{"id":"https://openalex.org/keywords/gene-nomenclature","display_name":"Gene nomenclature","score":0.4137200117111206},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.3056706190109253},{"id":"https://openalex.org/keywords/nomenclature","display_name":"Nomenclature","score":0.1216486394405365},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11766546964645386},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.09726831316947937},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.09158840775489807}],"concepts":[{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.79129958152771},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7354726791381836},{"id":"https://openalex.org/C204160518","wikidata":"https://www.wikidata.org/wiki/Q122653","display_name":"Numeral system","level":2,"score":0.7297345995903015},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5568650960922241},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5503572225570679},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5414746403694153},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.5411050319671631},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5157957077026367},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4454890191555023},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4292517900466919},{"id":"https://openalex.org/C62177273","wikidata":"https://www.wikidata.org/wiki/Q5531556","display_name":"Gene nomenclature","level":4,"score":0.4137200117111206},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3056706190109253},{"id":"https://openalex.org/C514705636","wikidata":"https://www.wikidata.org/wiki/Q863247","display_name":"Nomenclature","level":3,"score":0.1216486394405365},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11766546964645386},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.09726831316947937},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.09158840775489807},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D001330","descriptor_name":"Electronic Data Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001330","descriptor_name":"Electronic Data Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001330","descriptor_name":"Electronic Data Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007256","descriptor_name":"Information Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007256","descriptor_name":"Information Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007256","descriptor_name":"Information Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009626","descriptor_name":"Terminology as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009626","descriptor_name":"Terminology as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009626","descriptor_name":"Terminology as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"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":"D035843","descriptor_name":"Biomedical Research","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D035843","descriptor_name":"Biomedical Research","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D035843","descriptor_name":"Biomedical Research","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.1186/1471-2105-7-s5-s11","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-7-s5-s11","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-7-S5-S11","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:17254295","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/17254295","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:doaj.org/article:c2bb5a48b5c545119b3ec442097ac594","is_oa":false,"landing_page_url":"https://doaj.org/article/c2bb5a48b5c545119b3ec442097ac594","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 7, Iss Suppl 5, p S11 (2006)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:449381","is_oa":true,"landing_page_url":"http://europepmc.org/pmc/articles/PMC1764467","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:1764467","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/1764467","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-7-s5-s11","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-7-s5-s11","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-7-S5-S11","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":0.7300000190734863,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321040","display_name":"National Science Council","ror":"https://ror.org/02kv4zf79"},{"id":"https://openalex.org/F4320321041","display_name":"Academia Sinica","ror":"https://ror.org/05bxb3784"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2159640576.pdf","grobid_xml":"https://content.openalex.org/works/W2159640576.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W108101778","https://openalex.org/W189514790","https://openalex.org/W1483118642","https://openalex.org/W1524281572","https://openalex.org/W1592053870","https://openalex.org/W1661871015","https://openalex.org/W1747861911","https://openalex.org/W1934019294","https://openalex.org/W1937254975","https://openalex.org/W1973406306","https://openalex.org/W1991133427","https://openalex.org/W1996430422","https://openalex.org/W2004111828","https://openalex.org/W2008639146","https://openalex.org/W2008830554","https://openalex.org/W2009341227","https://openalex.org/W2012285872","https://openalex.org/W2021331223","https://openalex.org/W2034797903","https://openalex.org/W2056451646","https://openalex.org/W2061327015","https://openalex.org/W2067622664","https://openalex.org/W2068882115","https://openalex.org/W2087064593","https://openalex.org/W2114361266","https://openalex.org/W2118937875","https://openalex.org/W2127479124","https://openalex.org/W2133431243","https://openalex.org/W2139193890","https://openalex.org/W2144578941","https://openalex.org/W2147880316","https://openalex.org/W2151296343","https://openalex.org/W2152429541","https://openalex.org/W2156515921","https://openalex.org/W2162461580","https://openalex.org/W2399720833","https://openalex.org/W2603258515"],"related_works":["https://openalex.org/W1573992054","https://openalex.org/W1599690842","https://openalex.org/W2753053412","https://openalex.org/W2665157442","https://openalex.org/W3108840034","https://openalex.org/W4388169484","https://openalex.org/W2363259562","https://openalex.org/W3036937347","https://openalex.org/W2793132289","https://openalex.org/W3203550792"],"abstract_inverted_index":{"BACKGROUND:":[0],"Biomedical":[1],"named":[2,14,217],"entity":[3],"recognition":[4],"(Bio-NER)":[5],"is":[6,86,286,347],"a":[7,99,156,208,245,341],"challenging":[8],"problem":[9,202],"because,":[10],"in":[11,37,108,136,170,179,207,306],"general,":[12],"biomedical":[13,175,181],"entities":[15],"of":[16,56,98,166,174,222,248,251,281,338,344,363,388],"the":[17,53,83,96,152,171,180,201,220,230,241,252,268,279,327,350,361,365,386,394],"same":[18],"category":[19],"(e.g.,":[20,82,94,177,244],"proteins":[21],"and":[22,34,50,88,145,187,258,277,322,332,390],"genes)":[23],"do":[24],"not":[25,226],"follow":[26],"one":[27,79,91,211],"standard":[28],"nomenclature.":[29],"They":[30],"have":[31,46,303],"many":[32,189],"irregularities":[33],"sometimes":[35],"appear":[36],"ambiguous":[38],"contexts.":[39],"In":[40,192,376],"recent":[41],"years,":[42],"machine-learning":[43],"(ML)":[44],"approaches":[45,72],"become":[47],"increasingly":[48],"common":[49],"now":[51],"represent":[52],"cutting":[54],"edge":[55],"Bio-NER":[57,67,295,402],"technology.":[58],"This":[59,285],"paper":[60],"addresses":[61],"three":[62],"problems":[63],"faced":[64],"by":[65,203,267,329],"ML-based":[66,283,294,401],"systems.":[68],"First,":[69],"most":[70],"ML":[71,313],"usually":[73],"employ":[74,298],"singleton":[75,356],"features":[76,104,118,135,147],"that":[77,119,353,380,407],"comprise":[78],"linguistic":[80],"property":[81],"current":[84,253],"word":[85,254],"capitalized)":[87],"at":[89],"least":[90],"class":[92],"tag":[93],"B-protein,":[95],"beginning":[97],"protein":[100],"name).":[101],"However,":[102],"such":[103,275],"may":[105,236],"be":[106,114,124,129],"insufficient":[107],"cases":[109,406],"where":[110],"multiple":[111,121],"properties":[112,122],"must":[113],"considered.":[115],"Adding":[116,315],"conjunction":[117,134,317,373],"contain":[120],"can":[123,383,399],"beneficial,":[125],"but":[126,235],"it":[127],"would":[128],"infeasible":[130],"to":[131,161,214,273,370],"include":[132],"all":[133,205],"an":[137,163],"NER":[138],"model":[139],"since":[140],"memory":[141],"resources":[142],"are":[143,148],"limited":[144],"some":[146],"ineffective.":[149],"To":[150,291],"resolve":[151],"problem,":[153],"we":[154,195,297,378],"use":[155,263],"sequential":[157,366],"forward":[158,367],"search":[159,368],"algorithm":[160,272,369,398],"select":[162,371],"effective":[164,372],"set":[165],"features.":[167,191,357,392],"Second,":[168],"variations":[169],"numerical":[172,197,320,381],"parts":[173],"terms":[176],"\"2\"":[178],"term":[182,209],"IL2)":[183],"cause":[184],"data":[185],"sparseness":[186],"generate":[188],"redundant":[190,389],"this":[193],"case,":[194],"apply":[196],"normalization,":[198,321],"which":[199,302,346],"solves":[200],"replacing":[204],"numerals":[206],"with":[210,404],"representative":[212],"numeral":[213],"help":[215,400],"classify":[216],"entities.":[218],"Third,":[219],"assignment":[221],"NE":[223],"tags":[224],"does":[225],"depend":[227,237],"solely":[228],"on":[229,238],"target":[231],"word's":[232],"closest":[233],"neighbors,":[234],"words":[239],"outside":[240],"context":[242,246,410],"window":[243,247],"five":[249],"consists":[250],"plus":[255],"two":[256,259],"preceding":[257],"subsequent":[260],"words).":[261],"We":[262,359],"global":[264],"patterns":[265],"generated":[266],"Smith-Waterman":[269,395],"local":[270,396],"alignment":[271,397],"identify":[274],"structures":[276],"modify":[278],"results":[280],"our":[282,293,311],"tagger.":[284],"called":[287],"pattern-based":[288,324],"post-processing.":[289],"RESULTS:":[290],"develop":[292],"system,":[296],"conditional":[299],"random":[300],"fields,":[301],"performed":[304],"effectively":[305,384],"several":[307],"well-known":[308],"tasks,":[309],"as":[310],"underlying":[312],"model.":[314],"selected":[316],"features,":[318],"applying":[319],"employing":[323],"post-processing":[325],"improve":[326],"F-scores":[328],"1.67%,":[330],"1.04%,":[331],"0.57%,":[333],"respectively.":[334],"The":[335],"combined":[336],"increase":[337],"3.28%":[339],"yields":[340],"total":[342],"score":[343],"72.98%,":[345],"better":[348],"than":[349],"baseline":[351],"system":[352],"only":[354],"uses":[355],"CONCLUSION:":[358],"demonstrate":[360],"benefits":[362],"using":[364],"feature":[374],"groups.":[375],"addition,":[377],"show":[379],"normalization":[382],"reduce":[385],"number":[387],"unseen":[391],"Furthermore,":[393],"deal":[403],"difficult":[405],"need":[408],"longer":[409],"windows.":[411]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}