{"id":"https://openalex.org/W2163107094","doi":"https://doi.org/10.1093/bioinformatics/btg1023","title":"GENIA corpus\u2014a semantically annotated corpus for bio-textmining","display_name":"GENIA corpus\u2014a semantically annotated corpus for bio-textmining","publication_year":2003,"publication_date":"2003-07-03","ids":{"openalex":"https://openalex.org/W2163107094","doi":"https://doi.org/10.1093/bioinformatics/btg1023","mag":"2163107094","pmid":"https://pubmed.ncbi.nlm.nih.gov/12855455"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btg1023","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg1023","pdf_url":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110336982","display_name":"JD Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I4210086780","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19","country_code":"JP","type":"government","lineage":["https://openalex.org/I4210086780"]},{"id":"https://openalex.org/I4210159476","display_name":"Science and Technology Corporation (United States)","ror":"https://ror.org/05pw5zy84","country_code":"US","type":"company","lineage":["https://openalex.org/I4210159476"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"J.-D. Kim","raw_affiliation_strings":["CREST, Japan Science and Technology Corporation, Hongo, Bunkyo-ku, Tokyo, 113-0033, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CREST, Japan Science and Technology Corporation, Hongo, Bunkyo-ku, Tokyo, 113-0033, Japan","institution_ids":["https://openalex.org/I4210159476","https://openalex.org/I4210086780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007825608","display_name":"Tomoko Ohta","orcid":"https://orcid.org/0000-0002-9418-8352"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"T. Ohta","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068056695","display_name":"Yuka Tateisi","orcid":"https://orcid.org/0000-0002-3813-5782"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Y. Tateisi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5112016879","display_name":"J Tsujii","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J. Tsujii","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":14.2063,"has_fulltext":false,"cited_by_count":1243,"citation_normalized_percentile":{"value":0.99465158,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"19","issue":"suppl_1","first_page":"i180","last_page":"i182"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.998199999332428,"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":0.998199999332428,"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/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.972599983215332,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9275000095367432,"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/computer-science","display_name":"Computer science","score":0.8874610066413879},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.755037248134613},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6972267031669617},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6355922818183899},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5503774881362915},{"id":"https://openalex.org/keywords/biomedical-text-mining","display_name":"Biomedical text mining","score":0.41262978315353394},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38451528549194336},{"id":"https://openalex.org/keywords/text-mining","display_name":"Text mining","score":0.22161096334457397}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8874610066413879},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.755037248134613},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6972267031669617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6355922818183899},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5503774881362915},{"id":"https://openalex.org/C165141518","wikidata":"https://www.wikidata.org/wiki/Q4915126","display_name":"Biomedical text mining","level":3,"score":0.41262978315353394},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38451528549194336},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.22161096334457397},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"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":"D001695","descriptor_name":"Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D001695","descriptor_name":"Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D001695","descriptor_name":"Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004282","descriptor_name":"Documentation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004282","descriptor_name":"Documentation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004282","descriptor_name":"Documentation","qualifier_ui":null,"qualifier_name":null,"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":"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":"D010506","descriptor_name":"Periodicals as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010506","descriptor_name":"Periodicals as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010506","descriptor_name":"Periodicals as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016206","descriptor_name":"Databases, Bibliographic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016206","descriptor_name":"Databases, Bibliographic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016206","descriptor_name":"Databases, Bibliographic","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":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":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btg1023","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg1023","pdf_url":null,"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:12855455","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/12855455","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}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8700000047683716}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W1482328859","https://openalex.org/W1549026077"],"related_works":["https://openalex.org/W1657880117","https://openalex.org/W2595172197","https://openalex.org/W2127970246","https://openalex.org/W2084856301","https://openalex.org/W1001352512","https://openalex.org/W4382618745","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W1987128138","https://openalex.org/W2339319059"],"abstract_inverted_index":{"Abstract":[0],"Motivation:":[1],"Natural":[2,98],"language":[3],"processing":[4],"(NLP)":[5],"methods":[6],"are":[7],"regarded":[8],"as":[9],"being":[10,44],"useful":[11],"to":[12,46,50],"raise":[13],"the":[14],"potential":[15],"of":[16,24,29,63],"text":[17],"mining":[18],"from":[19],"biological":[20,82],"literature.":[21],"The":[22],"lack":[23],"an":[25],"extensively":[26],"annotated":[27],"corpus":[28,42,59,86],"this":[30],"literature,":[31],"however,":[32],"causes":[33],"a":[34],"major":[35],"bottleneck":[36],"for":[37,55,81],"applying":[38],"NLP":[39,52],"techniques.":[40],"GENIA":[41,58,85],"is":[43,87],"developed":[45],"provide":[47],"reference":[48],"materials":[49],"let":[51],"techniques":[53],"work":[54],"bio-textmining.":[56],"Results:":[57],"version":[60],"3.0":[61],"consisting":[62],"2000":[64],"MEDLINE":[65],"abstracts":[66],"has":[67],"been":[68],"released":[69],"with":[70],"more":[71],"than":[72],"400":[73],"000":[74,79],"words":[75],"and":[76],"almost":[77],"100":[78],"annotations":[80],"terms.":[83],"Availability:":[84],"freely":[88],"available":[89],"at":[90],"http://www-tsujii.is.s.u-tokyo.ac.jp/GENIA":[91],"Keywords:":[92],"Text":[93],"Mining,":[94],"Information":[95],"Extraction,":[96],"Corpus,":[97],"Language":[99],"Processing,":[100],"Computational":[101],"Molecular":[102],"Biology":[103],"*To":[104],"whom":[105],"correspondence":[106],"should":[107],"be":[108],"addressed.":[109]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":55},{"year":2024,"cited_by_count":55},{"year":2023,"cited_by_count":72},{"year":2022,"cited_by_count":80},{"year":2021,"cited_by_count":73},{"year":2020,"cited_by_count":57},{"year":2019,"cited_by_count":81},{"year":2018,"cited_by_count":51},{"year":2017,"cited_by_count":66},{"year":2016,"cited_by_count":40},{"year":2015,"cited_by_count":45},{"year":2014,"cited_by_count":83},{"year":2013,"cited_by_count":43},{"year":2012,"cited_by_count":47}],"updated_date":"2026-06-13T07:54:00.901334","created_date":"2025-10-10T00:00:00"}