{"id":"https://openalex.org/W2131449610","doi":"https://doi.org/10.1093/bioinformatics/bti733","title":"Automatic term list generation for entity tagging","display_name":"Automatic term list generation for entity tagging","publication_year":2005,"publication_date":"2005-10-25","ids":{"openalex":"https://openalex.org/W2131449610","doi":"https://doi.org/10.1093/bioinformatics/bti733","mag":"2131449610","pmid":"https://pubmed.ncbi.nlm.nih.gov/16249261"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bti733","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti733","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/22/6/651/48838571/bioinformatics_22_6_651.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/22/6/651/48838571/bioinformatics_22_6_651.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054561921","display_name":"Ted Sandler","orcid":null},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ted Sandler","raw_affiliation_strings":["Department of Computer and Information Science, University of Pennsylvania \u00a0 3330 Walnut Street, Philadelphia, PA 19104, USA","Department of Computer and Information Science, University of Pennsylvania, 3330 Walnut Street, Philadelphia, PA 19104, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, University of Pennsylvania \u00a0 3330 Walnut Street, Philadelphia, PA 19104, USA","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"Department of Computer and Information Science, University of Pennsylvania, 3330 Walnut Street, Philadelphia, PA 19104, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068071252","display_name":"Andrew I. Schein","orcid":null},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew I. Schein","raw_affiliation_strings":["Department of Computer and Information Science, University of Pennsylvania \u00a0 3330 Walnut Street, Philadelphia, PA 19104, USA","Department of Computer and Information Science, University of Pennsylvania, 3330 Walnut Street, Philadelphia, PA 19104, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, University of Pennsylvania \u00a0 3330 Walnut Street, Philadelphia, PA 19104, USA","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"Department of Computer and Information Science, University of Pennsylvania, 3330 Walnut Street, Philadelphia, PA 19104, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044944954","display_name":"Lyle Ungar","orcid":"https://orcid.org/0000-0003-2047-1443"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lyle H. Ungar","raw_affiliation_strings":["Department of Computer and Information Science, University of Pennsylvania \u00a0 3330 Walnut Street, Philadelphia, PA 19104, USA","Department of Computer and Information Science, University of Pennsylvania, 3330 Walnut Street, Philadelphia, PA 19104, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, University of Pennsylvania \u00a0 3330 Walnut Street, Philadelphia, PA 19104, USA","institution_ids":["https://openalex.org/I79576946"]},{"raw_affiliation_string":"Department of Computer and Information Science, University of Pennsylvania, 3330 Walnut Street, Philadelphia, PA 19104, USA","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5054561921"],"corresponding_institution_ids":["https://openalex.org/I79576946"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":0.5023,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.64111414,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"22","issue":"6","first_page":"651","last_page":"657"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.5328999757766724,"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":0.5328999757766724,"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/T11719","display_name":"Data Quality and Management","score":0.11320000141859055,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.09790000319480896,"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":0.8567795753479004},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.7625698447227478},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.6853095293045044},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6491705775260925},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.6436478495597839},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6229553818702698},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5922661423683167},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5879835486412048},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5376054048538208},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4203191101551056},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12507539987564087}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8567795753479004},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7625698447227478},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.6853095293045044},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6491705775260925},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.6436478495597839},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6229553818702698},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5922661423683167},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5879835486412048},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5376054048538208},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4203191101551056},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12507539987564087},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"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":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","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":true},{"descriptor_ui":"D004282","descriptor_name":"Documentation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D004282","descriptor_name":"Documentation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D004282","descriptor_name":"Documentation","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010506","descriptor_name":"Periodicals as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010506","descriptor_name":"Periodicals as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010506","descriptor_name":"Periodicals as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","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}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/bti733","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti733","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/22/6/651/48838571/bioinformatics_22_6_651.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:16249261","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16249261","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.87.8979","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.87.8979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ftp.informatik.rwth-aachen.de/Publications/CEUR-WS/Vol-148/smbm2005_sandler_abstract.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/bti733","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bti733","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/22/6/651/48838571/bioinformatics_22_6_651.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Life below water","id":"https://metadata.un.org/sdg/14","score":0.75}],"awards":[{"id":"https://openalex.org/G1721448359","display_name":null,"funder_award_id":"T32HG 0000461","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W73274768","https://openalex.org/W77787017","https://openalex.org/W130850236","https://openalex.org/W200042785","https://openalex.org/W1593045043","https://openalex.org/W1930023685","https://openalex.org/W2031868269","https://openalex.org/W2061611928","https://openalex.org/W2068737686","https://openalex.org/W2085678516","https://openalex.org/W2116780029","https://openalex.org/W2121227244","https://openalex.org/W2123084125","https://openalex.org/W2124602574","https://openalex.org/W2126276057","https://openalex.org/W2127314673","https://openalex.org/W2151296343","https://openalex.org/W2159799774","https://openalex.org/W2161669948","https://openalex.org/W2161890636","https://openalex.org/W2163918411","https://openalex.org/W2165625418","https://openalex.org/W2166776180","https://openalex.org/W2434205482","https://openalex.org/W2952509172","https://openalex.org/W2964023183","https://openalex.org/W4255198209","https://openalex.org/W4255387915","https://openalex.org/W4302585900","https://openalex.org/W6602999377","https://openalex.org/W6603134736","https://openalex.org/W6605282444","https://openalex.org/W6608051331","https://openalex.org/W6635456232","https://openalex.org/W6640516325","https://openalex.org/W6667909331","https://openalex.org/W6677145740","https://openalex.org/W6678277124","https://openalex.org/W6678583822","https://openalex.org/W6678759912","https://openalex.org/W6679063059","https://openalex.org/W6682170221","https://openalex.org/W6683666026","https://openalex.org/W6683704841","https://openalex.org/W6684177858","https://openalex.org/W6718170660","https://openalex.org/W6764734552"],"related_works":["https://openalex.org/W2382566571","https://openalex.org/W579810227","https://openalex.org/W2952780262","https://openalex.org/W2349321798","https://openalex.org/W2979495269","https://openalex.org/W2366686860","https://openalex.org/W2350859087","https://openalex.org/W2387118502","https://openalex.org/W4287688258","https://openalex.org/W3049211950"],"abstract_inverted_index":{"MOTIVATION:":[0],"Many":[1],"entity":[2],"taggers":[3],"and":[4,50,76,122],"information":[5],"extraction":[6],"systems":[7],"make":[8],"use":[9],"of":[10,12,14,66,74,81,88,105,131],"lists":[11,24,73,100,121,147],"terms":[13,75],"entities":[15],"such":[16],"as":[17,79,148,150,167],"people,":[18],"places,":[19],"genes":[20],"or":[21],"chemicals.":[22],"These":[23],"have":[25],"traditionally":[26],"been":[27],"constructed":[28],"manually.":[29],"We":[30],"show":[31,94,138],"that":[32,43,95,114,128,130,139,157],"distributional":[33,141],"clustering":[34,142],"methods":[35,143],"which":[36],"group":[37],"words":[38,49],"based":[39],"on":[40,71,85],"the":[41,64,91,103,132],"contexts":[42],"they":[44,158],"appear":[45],"in,":[46],"including":[47],"neighboring":[48],"syntactic":[51],"relations":[52],"extracted":[53],"using":[54,77,118],"a":[55,82,86,106,112,126],"shallow":[56],"parser,":[57],"can":[58,159],"be":[59,160],"used":[60,161,175],"to":[61,111,125,162,168],"aid":[62],"in":[63,176],"construction":[65],"term":[67,99],"lists.":[68,134],"RESULTS:":[69],"Experiments":[70],"learning":[72],"them":[78],"part":[80],"gene":[83,109],"tagger":[84,110],"corpus":[87],"abstracts":[89],"from":[90,181],"scientific":[92],"literature":[93],"our":[96],"automatically":[97],"generated":[98,152],"significantly":[101],"boost":[102],"precision":[104],"state-of-the-art":[107],"CRF-based":[108],"degree":[113,127],"is":[115,179],"competitive":[116],"with":[117],"hand":[119],"curated":[120],"boosts":[123],"recall":[124],"surpasses":[129],"hand-curated":[133],"Our":[135],"results":[136],"also":[137],"these":[140],"do":[144],"not":[145],"generate":[146],"helpful":[149],"those":[151],"by":[153],"supervised":[154,164],"techniques,":[155],"but":[156],"complement":[163],"techniques":[165],"so":[166],"obtain":[169],"better":[170],"performance.":[171],"AVAILABILITY:":[172],"The":[173],"code":[174],"this":[177],"paper":[178],"available":[180],"http://www.cis.upenn.edu/datamining/software_dist/autoterm/":[182]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-23T06:36:01.041984","created_date":"2025-10-10T00:00:00"}