{"id":"https://openalex.org/W1985884332","doi":"https://doi.org/10.1017/s1351324905003967","title":"The importance of the lexicon in tagging biological text","display_name":"The importance of the lexicon in tagging biological text","publication_year":2005,"publication_date":"2005-12-14","ids":{"openalex":"https://openalex.org/W1985884332","doi":"https://doi.org/10.1017/s1351324905003967","mag":"1985884332"},"language":"en","primary_location":{"id":"doi:10.1017/s1351324905003967","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324905003967","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110649152","display_name":"Lawrence H. Smith","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"LAWRENCE H. SMITH","raw_affiliation_strings":["National Center for Biotechnology Information, National Library of Medicine, Bethesda, MD, USA e-mail:","National Center for Biotechnology Information, National Library of Medicine, Bethesda, MD, USA e-mail: lsmith@ncbi.nlm.nih.gov, wilbur@ncbi.nlm.nih.gov"],"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine, Bethesda, MD, USA e-mail:","institution_ids":["https://openalex.org/I4210109390"]},{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine, Bethesda, MD, USA e-mail: lsmith@ncbi.nlm.nih.gov, wilbur@ncbi.nlm.nih.gov","institution_ids":["https://openalex.org/I4210109390"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046137010","display_name":"Thomas C. Rindflesch","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"THOMAS C. RINDFLESCH","raw_affiliation_strings":["Lister Hill National Center for Biomedical Communications, National Library of Medicine, Bethesda, MD","Lister Hill National Center for Biomedical Communications, National Library of Medicine, Bethesda, MD, USA tcr@nlm.nih.gov#TAB#"],"affiliations":[{"raw_affiliation_string":"Lister Hill National Center for Biomedical Communications, National Library of Medicine, Bethesda, MD","institution_ids":["https://openalex.org/I4210109390"]},{"raw_affiliation_string":"Lister Hill National Center for Biomedical Communications, National Library of Medicine, Bethesda, MD, USA tcr@nlm.nih.gov#TAB#","institution_ids":["https://openalex.org/I4210109390"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111895206","display_name":"W. John Wilbur","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"W. JOHN WILBUR","raw_affiliation_strings":["National Center for Biotechnology Information, National Library of Medicine, Bethesda, MD, USA e-mail:","National Center for Biotechnology Information, National Library of Medicine, Bethesda, MD, USA e-mail: lsmith@ncbi.nlm.nih.gov, wilbur@ncbi.nlm.nih.gov"],"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine, Bethesda, MD, USA e-mail:","institution_ids":["https://openalex.org/I4210109390"]},{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine, Bethesda, MD, USA e-mail: lsmith@ncbi.nlm.nih.gov, wilbur@ncbi.nlm.nih.gov","institution_ids":["https://openalex.org/I4210109390"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5110649152"],"corresponding_institution_ids":["https://openalex.org/I4210109390"],"apc_list":null,"apc_paid":null,"fwci":1.755,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.86544544,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"12","issue":"4","first_page":"335","last_page":"351"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9987999796867371,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.9263633489608765},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.907159686088562},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7397302389144897},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.605692446231842},{"id":"https://openalex.org/keywords/part-of-speech-tagging","display_name":"Part-of-speech tagging","score":0.5480539798736572},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5140191316604614},{"id":"https://openalex.org/keywords/part-of-speech","display_name":"Part of speech","score":0.4379974603652954},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33072298765182495}],"concepts":[{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.9263633489608765},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.907159686088562},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7397302389144897},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.605692446231842},{"id":"https://openalex.org/C2780684714","wikidata":"https://www.wikidata.org/wiki/Q1271424","display_name":"Part-of-speech tagging","level":3,"score":0.5480539798736572},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5140191316604614},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.4379974603652954},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33072298765182495},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1017/s1351324905003967","is_oa":false,"landing_page_url":"https://doi.org/10.1017/s1351324905003967","pdf_url":null,"source":{"id":"https://openalex.org/S18088403","display_name":"Natural Language Engineering","issn_l":"1351-3249","issn":["1351-3249","1469-8110"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311721","host_organization_name":"Cambridge University Press","host_organization_lineage":["https://openalex.org/P4310311721","https://openalex.org/P4310311702"],"host_organization_lineage_names":["Cambridge University Press","University of Cambridge"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Natural Language Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.75,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1524688041","https://openalex.org/W1632114991","https://openalex.org/W1773803948","https://openalex.org/W1968953480","https://openalex.org/W1976241232","https://openalex.org/W1980860611","https://openalex.org/W2046224275","https://openalex.org/W2079355893","https://openalex.org/W2079656678","https://openalex.org/W2081687495","https://openalex.org/W2110529160","https://openalex.org/W2113641473","https://openalex.org/W2125838338","https://openalex.org/W2127241285","https://openalex.org/W2135843243","https://openalex.org/W2796493717"],"related_works":["https://openalex.org/W4293870971","https://openalex.org/W1831473261","https://openalex.org/W1999382833","https://openalex.org/W1965453504","https://openalex.org/W2396342956","https://openalex.org/W2169508526","https://openalex.org/W2486838646","https://openalex.org/W2949108231","https://openalex.org/W1985884332","https://openalex.org/W2626026432"],"abstract_inverted_index":{"A":[0,68],"part-of-speech":[1],"tagger":[2,59,73,104],"is":[3,49,74,100],"a":[4,57,107],"fundamental":[5],"and":[6,47,110],"indispensable":[7],"tool":[8],"in":[9,30,89],"computational":[10],"linguistics,":[11],"typically":[12],"employed":[13],"at":[14],"the":[15,72,79,83,95,98],"critical":[16],"early":[17],"stages":[18],"of":[19,71],"processing.":[20],"Although":[21],"taggers":[22],"are":[23],"widely":[24],"available":[25],"that":[26,60,97],"achieve":[27],"high":[28],"accuracy":[29,64,105],"very":[31],"general":[32],"domains,":[33,46],"these":[34],"do":[35],"not":[36],"perform":[37],"nearly":[38],"as":[39,101,106],"well":[40],"when":[41],"applied":[42],"to":[43,103],"novel":[44],"specialized":[45],"this":[48],"especially":[50],"true":[51],"with":[52],"biological":[53],"text.":[54],"We":[55,91],"present":[56,92],"stochastic":[58],"achieves":[61],"over":[62],"97.44%":[63],"on":[65],"MEDLINE":[66],"abstracts.":[67],"primary":[69],"component":[70],"its":[75],"lexicon":[76,99],"which":[77],"enumerates":[78],"permitted":[80],"parts-of-speech":[81],"for":[82,94],"10000":[84],"words":[85],"most":[86],"frequently":[87],"occurring":[88],"MEDLINE.":[90],"evidence":[93],"conclusion":[96],"vital":[102],"training":[108],"corpus,":[109],"more":[111],"important":[112],"than":[113],"previously":[114],"thought.":[115]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}