{"id":"https://openalex.org/W2093370758","doi":"https://doi.org/10.1145/1815330.1815346","title":"Investigator name recognition from medical journal articles","display_name":"Investigator name recognition from medical journal articles","publication_year":2010,"publication_date":"2010-06-09","ids":{"openalex":"https://openalex.org/W2093370758","doi":"https://doi.org/10.1145/1815330.1815346","mag":"2093370758"},"language":"en","primary_location":{"id":"doi:10.1145/1815330.1815346","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1815330.1815346","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th IAPR International Workshop on Document Analysis Systems","raw_type":"proceedings-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/A5101656517","display_name":"Xiaoli Zhang","orcid":"https://orcid.org/0000-0002-9790-5636"},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"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":"Xiaoli Zhang","raw_affiliation_strings":["National Library of Medicine, Lister Hill National Center for Biomedical Communications, Rockville Pike, Bethesda","National Library of Medicine, Lister Hill National Center for Biomedical Communications, Rockville Pike, Bethesda#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Library of Medicine, Lister Hill National Center for Biomedical Communications, Rockville Pike, Bethesda","institution_ids":["https://openalex.org/I4210109390"]},{"raw_affiliation_string":"National Library of Medicine, Lister Hill National Center for Biomedical Communications, Rockville Pike, Bethesda#TAB#","institution_ids":["https://openalex.org/I1299303238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027451971","display_name":"Jie Zou","orcid":"https://orcid.org/0000-0003-2303-3772"},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"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":"Jie Zou","raw_affiliation_strings":["National Library of Medicine, Lister Hill National Center for Biomedical Communications, Rockville Pike, Bethesda","National Library of Medicine, Lister Hill National Center for Biomedical Communications, Rockville Pike, Bethesda#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Library of Medicine, Lister Hill National Center for Biomedical Communications, Rockville Pike, Bethesda","institution_ids":["https://openalex.org/I4210109390"]},{"raw_affiliation_string":"National Library of Medicine, Lister Hill National Center for Biomedical Communications, Rockville Pike, Bethesda#TAB#","institution_ids":["https://openalex.org/I1299303238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101509629","display_name":"Daniel Le","orcid":"https://orcid.org/0000-0002-0220-6366"},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"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":"Daniel X. Le","raw_affiliation_strings":["National Library of Medicine, Lister Hill National Center for Biomedical Communications, Rockville Pike, Bethesda","National Library of Medicine, Lister Hill National Center for Biomedical Communications, Rockville Pike, Bethesda#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Library of Medicine, Lister Hill National Center for Biomedical Communications, Rockville Pike, Bethesda","institution_ids":["https://openalex.org/I4210109390"]},{"raw_affiliation_string":"National Library of Medicine, Lister Hill National Center for Biomedical Communications, Rockville Pike, Bethesda#TAB#","institution_ids":["https://openalex.org/I1299303238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103701816","display_name":"George R. Thoma","orcid":null},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"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":"George R. Thoma","raw_affiliation_strings":["National Library of Medicine, Lister Hill National Center for Biomedical Communications, Rockville Pike, Bethesda","National Library of Medicine, Lister Hill National Center for Biomedical Communications, Rockville Pike, Bethesda#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Library of Medicine, Lister Hill National Center for Biomedical Communications, Rockville Pike, Bethesda","institution_ids":["https://openalex.org/I4210109390"]},{"raw_affiliation_string":"National Library of Medicine, Lister Hill National Center for Biomedical Communications, Rockville Pike, Bethesda#TAB#","institution_ids":["https://openalex.org/I1299303238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4084,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.63639021,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"121","last_page":"128"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9987999796867371,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9940000176429749,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7976413369178772},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.7667014002799988},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6553575396537781},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6478254199028015},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6021202802658081},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.594641387462616},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5146037340164185},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4966314435005188},{"id":"https://openalex.org/keywords/citation","display_name":"Citation","score":0.47453391551971436},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4351545572280884},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.42048734426498413},{"id":"https://openalex.org/keywords/medline","display_name":"MEDLINE","score":0.41165587306022644},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2059389054775238}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7976413369178772},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.7667014002799988},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6553575396537781},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6478254199028015},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6021202802658081},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.594641387462616},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5146037340164185},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4966314435005188},{"id":"https://openalex.org/C2778805511","wikidata":"https://www.wikidata.org/wiki/Q1713","display_name":"Citation","level":2,"score":0.47453391551971436},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4351545572280884},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.42048734426498413},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.41165587306022644},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2059389054775238},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1815330.1815346","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1815330.1815346","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th IAPR International Workshop on Document Analysis Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320615","display_name":"Lister Institute of Preventive Medicine","ror":"https://ror.org/03356n642"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2169610","https://openalex.org/W163605501","https://openalex.org/W1520377376","https://openalex.org/W1528620860","https://openalex.org/W1563088657","https://openalex.org/W1564518192","https://openalex.org/W1934019294","https://openalex.org/W2006439165","https://openalex.org/W2020278455","https://openalex.org/W2030684440","https://openalex.org/W2031248101","https://openalex.org/W2047782770","https://openalex.org/W2072167633","https://openalex.org/W2077941393","https://openalex.org/W2089933214","https://openalex.org/W2114361266","https://openalex.org/W2119821739","https://openalex.org/W2139212933","https://openalex.org/W2141099517","https://openalex.org/W2148603752","https://openalex.org/W2149430911","https://openalex.org/W2149684865","https://openalex.org/W2152540201","https://openalex.org/W2153635508","https://openalex.org/W2156909104","https://openalex.org/W2157791002","https://openalex.org/W2398591267","https://openalex.org/W2429914308","https://openalex.org/W3004533406","https://openalex.org/W3193477162","https://openalex.org/W4230674625","https://openalex.org/W7071374342"],"related_works":["https://openalex.org/W2334378031","https://openalex.org/W2916255597","https://openalex.org/W2999302224","https://openalex.org/W3091569222","https://openalex.org/W4241018868","https://openalex.org/W1495833002","https://openalex.org/W2075635421","https://openalex.org/W2964631078","https://openalex.org/W3160627956","https://openalex.org/W3006227201"],"abstract_inverted_index":{"Automated":[0],"extraction":[1,73],"of":[2,16,34,56,74,94,128,152,202,218],"bibliographic":[3,25],"information":[4],"from":[5,87,206],"journal":[6],"articles":[7],"is":[8,30,59,69,77,119],"key":[9],"to":[10,39,91,111,121,136,165,171,182,212],"the":[11,40,44,54,92,99,102,158,189,200,219],"affordable":[12],"creation":[13],"and":[14,125,148,160],"maintenance":[15],"citation":[17],"databases,":[18],"such":[19,57],"as":[20,51],"MEDLINE\u00ae.":[21],"A":[22],"newly":[23],"required":[24],"field":[26],"in":[27,43,80,98,114,180],"this":[28,138],"database":[29],"\"Investigator":[31],"Names\":":[32],"names":[33,58,76,110,127],"people":[35],"who":[36,47],"have":[37],"contributed":[38],"research":[41],"addressed":[42],"article,":[45],"but":[46,85],"are":[48],"not":[49],"listed":[50],"authors.":[52],"Since":[53],"number":[55],"often":[60],"large,":[61],"several":[62],"score":[63],"or":[64,214],"more,":[65],"their":[66],"manual":[67],"entry":[68],"prohibitive.":[70],"The":[71],"automated":[72],"these":[75,203],"a":[78,115,173],"problem":[79],"Named":[81],"Entity":[82],"Recognition":[83],"(NER),":[84],"differs":[86],"typical":[88],"NER":[89],"due":[90],"absence":[93],"normal":[95],"English":[96],"grammar":[97],"text":[100],"containing":[101],"names.":[103],"In":[104,163],"addition,":[105],"since":[106],"MEDLINE":[107],"conventions":[108],"require":[109],"be":[112],"expressed":[113],"particular":[116],"format,":[117],"it":[118],"necessary":[120],"identify":[122],"both":[123,151],"first":[124],"last":[126],"each":[129],"investigator,":[130],"an":[131],"additional":[132],"challenge.":[133],"We":[134],"seek":[135],"automate":[137],"task":[139],"through":[140],"two":[141],"machine":[142],"learning":[143,191],"approaches:":[144],"Support":[145],"Vector":[146],"Machine":[147],"structural":[149,168,220],"SVM,":[150,167],"which":[153],"show":[154],"good":[155],"performance":[156,210],"at":[157,188],"word":[159],"chunk":[161],"levels.":[162],"contrast":[164],"traditional":[166],"SVM":[169,187,209],"attempts":[170],"learn":[172],"sequence":[174],"by":[175],"using":[176,194],"contextual":[177,195,204],"label":[178],"features":[179,205],"addition":[181,201],"observational":[183],"features.":[184,197],"It":[185],"outperforms":[186],"initial":[190],"stage":[192],"without":[193],"observation":[196],"However,":[198],"with":[199],"neighboring":[207],"tokens,":[208],"improves":[211],"match":[213],"slightly":[215],"exceed":[216],"that":[217],"SVM.":[221]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}