{"id":"https://openalex.org/W2048140075","doi":"https://doi.org/10.1186/1471-2105-6-s1-s3","title":"GENETAG: a tagged corpus for gene/protein named entity recognition","display_name":"GENETAG: a tagged corpus for gene/protein named entity recognition","publication_year":2005,"publication_date":"2005-05-01","ids":{"openalex":"https://openalex.org/W2048140075","doi":"https://doi.org/10.1186/1471-2105-6-s1-s3","mag":"2048140075","pmid":"https://pubmed.ncbi.nlm.nih.gov/15960837"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-6-s1-s3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-6-s1-s3","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-6-S1-S3","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/10.1186/1471-2105-6-S1-S3","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029205618","display_name":"Lorraine Tanabe","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":true,"raw_author_name":"Lorraine Tanabe","raw_affiliation_strings":["National Center for Biotechnology Information, National Library of Medicine, NIH, 8600 Rockville Pike, Bethesda, MD 20894, USA. tanabe@ncbi.nlm.nih.gov","National Center for Biotechnology Information, National Library of Medicine/NIH, Bethesda, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine, NIH, 8600 Rockville Pike, Bethesda, MD 20894, USA. tanabe@ncbi.nlm.nih.gov","institution_ids":["https://openalex.org/I4210109390"]},{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine/NIH, Bethesda, USA","institution_ids":["https://openalex.org/I1299303238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068777093","display_name":"Natalie Xie","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":"Natalie Xie","raw_affiliation_strings":["National Center for Biotechnology Information, National Library of Medicine, NIH, 8600 Rockville Pike, Bethesda, MD, 20894, USA","National Center for Biotechnology Information, National Library of Medicine/NIH, Bethesda, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine, NIH, 8600 Rockville Pike, Bethesda, MD, 20894, USA","institution_ids":["https://openalex.org/I4210109390"]},{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine/NIH, Bethesda, USA","institution_ids":["https://openalex.org/I1299303238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039388441","display_name":"Lynne H Thom","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142207","display_name":"Consolidated Safety Services-Dynamac (United States)","ror":"https://ror.org/03mz0by90","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142207"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lynne H Thom","raw_affiliation_strings":["Consolidated Safety Services, 10335 Democracy Lane, Suite 202, Fairfax, VA, 22030, USA","Consolidated Safety Services, Fairfax, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Consolidated Safety Services, 10335 Democracy Lane, Suite 202, Fairfax, VA, 22030, USA","institution_ids":["https://openalex.org/I4210142207"]},{"raw_affiliation_string":"Consolidated Safety Services, Fairfax, USA","institution_ids":["https://openalex.org/I4210142207"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007444890","display_name":"Wayne T. Matten","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142207","display_name":"Consolidated Safety Services-Dynamac (United States)","ror":"https://ror.org/03mz0by90","country_code":"US","type":"company","lineage":["https://openalex.org/I4210142207"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wayne Matten","raw_affiliation_strings":["Consolidated Safety Services, 10335 Democracy Lane, Suite 202, Fairfax, VA, 22030, USA","Consolidated Safety Services, Fairfax, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Consolidated Safety Services, 10335 Democracy Lane, Suite 202, Fairfax, VA, 22030, USA","institution_ids":["https://openalex.org/I4210142207"]},{"raw_affiliation_string":"Consolidated Safety Services, Fairfax, USA","institution_ids":["https://openalex.org/I4210142207"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111895206","display_name":"W. John Wilbur","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":"W John Wilbur","raw_affiliation_strings":["National Center for Biotechnology Information, National Library of Medicine, NIH, 8600 Rockville Pike, Bethesda, MD, 20894, USA","National Center for Biotechnology Information, National Library of Medicine/NIH, Bethesda, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine, NIH, 8600 Rockville Pike, Bethesda, MD, 20894, USA","institution_ids":["https://openalex.org/I4210109390"]},{"raw_affiliation_string":"National Center for Biotechnology Information, National Library of Medicine/NIH, Bethesda, USA","institution_ids":["https://openalex.org/I1299303238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5029205618"],"corresponding_institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210109390"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":4.9285,"has_fulltext":true,"cited_by_count":231,"citation_normalized_percentile":{"value":0.959434,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":"6","issue":"S1","first_page":"S3","last_page":"S3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9807999730110168,"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":0.9807999730110168,"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":0.012299999594688416,"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":0.0015999999595806003,"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/dna-microarray","display_name":"DNA microarray","score":0.5971264243125916},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5434376001358032},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.4845789670944214},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.4385235905647278},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43347060680389404},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4327782392501831},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.38112306594848633},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.36198651790618896},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.25780266523361206},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0666782557964325}],"concepts":[{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.5971264243125916},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5434376001358032},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.4845789670944214},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.4385235905647278},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43347060680389404},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4327782392501831},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.38112306594848633},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.36198651790618896},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.25780266523361206},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0666782557964325},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005796","descriptor_name":"Genes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005796","descriptor_name":"Genes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005796","descriptor_name":"Genes","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"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":"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":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016239","descriptor_name":"MEDLINE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016239","descriptor_name":"MEDLINE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016239","descriptor_name":"MEDLINE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021641","descriptor_name":"Recognition, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D021641","descriptor_name":"Recognition, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D021641","descriptor_name":"Recognition, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1186/1471-2105-6-s1-s3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-6-s1-s3","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-6-S1-S3","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:15960837","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15960837","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:pubmedcentral.nih.gov:1869017","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/1869017","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:10.1186/1471-2105-6-s1-s3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-6-s1-s3","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-6-S1-S3","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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2048140075.pdf","grobid_xml":"https://content.openalex.org/works/W2048140075.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W1555244713","https://openalex.org/W1632114991","https://openalex.org/W2018874418","https://openalex.org/W2134769633","https://openalex.org/W2144001613","https://openalex.org/W2163107094","https://openalex.org/W2284943364"],"related_works":["https://openalex.org/W2078793151","https://openalex.org/W3017222382","https://openalex.org/W3128216712","https://openalex.org/W3136915866","https://openalex.org/W4390279576","https://openalex.org/W2886890203","https://openalex.org/W4313535650","https://openalex.org/W2287770975","https://openalex.org/W2991463832","https://openalex.org/W3215585698"],"abstract_inverted_index":{"BACKGROUND:":[0],"Named":[1],"entity":[2,182],"recognition":[3],"(NER)":[4],"is":[5,23,40],"an":[6,206],"important":[7],"first":[8,89],"step":[9],"for":[10,36,65,73,91,169],"text":[11],"mining":[12],"the":[13,17,46,53,74,84,123,145,163,180,189,203,243],"biomedical":[14,20],"literature.":[15],"Evaluating":[16],"performance":[18,204],"of":[19,32,48,57,61,83,133,193,202,205,216,239,274],"NER":[21,39,207],"systems":[22],"impossible":[24],"without":[25],"a":[26,34,41,59,118,130,138,141,198],"standardized":[27],"test":[28],"corpus.":[29],"The":[30,111,214,228],"annotation":[31,56,215],"such":[33],"corpus":[35,60],"gene/protein":[37,49,66,119,134,164],"name":[38,120],"difficult":[42],"process":[43],"due":[44],"to":[45,94,128,137,148,150,162,183,234,242],"complexity":[47],"names.":[50],"We":[51],"describe":[52],"construction":[54],"and":[55,100,103,122,260,263],"GENETAG,":[58],"20K":[62,113],"MEDLINE":[63,86],"sentences":[64,70,87,106,114],"NER.":[67],"15K":[68],"GENETAG":[69,156,217,257],"were":[71,88,107,115,125,230],"used":[72],"BioCreAtIvE":[75],"Task":[76],"1A":[77],"Competition.":[78],"RESULTS:":[79],"To":[80],"ensure":[81],"heterogeneity":[82],"corpus,":[85],"scored":[90],"term":[92],"similarity":[93],"documents":[95],"with":[96,159,172],"known":[97],"gene":[98],"names,":[99],"10K":[101,104],"high-":[102],"low-scoring":[105],"chosen":[108],"at":[109,269],"random.":[110],"original":[112],"run":[116],"through":[117],"tagger,":[121],"results":[124,196],"modified":[126],"manually":[127],"reflect":[129],"wide":[131],"definition":[132],"names":[135,165],"subject":[136],"specificity":[139],"constraint,":[140],"rule":[142],"that":[143],"required":[144,218],"tagged":[146,181],"entities":[147],"refer":[149],"specific":[151],"entities.":[152],"Each":[153],"sentence":[154,190],"in":[155,188,197],"was":[157],"annotated":[158],"acceptable":[160],"alternatives":[161],"it":[166],"contained,":[167],"allowing":[168],"partial":[170,211],"matching":[171],"semantic":[173],"constraints.":[174],"Semantic":[175],"constraints":[176,195],"are":[177,266],"rules":[178],"requiring":[179],"contain":[184],"its":[185],"true":[186],"meaning":[187],"context.":[191],"Application":[192],"these":[194],"more":[199,252],"meaningful":[200],"measure":[201],"system":[208,240],"than":[209,254],"unrestricted":[210],"matching.":[212],"CONCLUSION:":[213],"intricate":[219],"manual":[220],"judgments":[221],"by":[222],"annotators":[223],"which":[224],"hindered":[225],"tagging":[226],"consistency.":[227],"data":[229,262],"pre-segmented":[231],"into":[232],"words,":[233],"provide":[235],"indices":[236,248],"supporting":[237],"comparison":[238],"responses":[241],"\"gold":[244],"standard\".":[245],"However,":[246],"character-based":[247],"would":[249],"have":[250],"been":[251],"robust":[253],"word-based":[255],"indices.":[256],"Train,":[258],"Test":[259],"Round1":[261],"ancillary":[264],"programs":[265],"freely":[267],"available":[268],"ftp://ftp.ncbi.nlm.nih.gov/pub/tanabe/GENETAG.tar.gz.":[270],"A":[271],"newer":[272],"version":[273],"GENETAG-05,":[275],"will":[276],"be":[277],"released":[278],"later":[279],"this":[280],"year.":[281]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":12},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":13},{"year":2013,"cited_by_count":21},{"year":2012,"cited_by_count":22}],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-10T00:00:00"}
