{"id":"https://openalex.org/W2131887446","doi":"https://doi.org/10.1186/1471-2105-10-403","title":"Investigating heterogeneous protein annotations toward cross-corpora utilization","display_name":"Investigating heterogeneous protein annotations toward cross-corpora utilization","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2131887446","doi":"https://doi.org/10.1186/1471-2105-10-403","mag":"2131887446","pmid":"https://pubmed.ncbi.nlm.nih.gov/19995463"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-10-403","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-10-403","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/1471-2105-10-403","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/track/pdf/10.1186/1471-2105-10-403","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100371984","display_name":"Yue Wang","orcid":"https://orcid.org/0000-0002-0278-2347"},"institutions":[{"id":"https://openalex.org/I161296585","display_name":"Tokyo University of Science","ror":"https://ror.org/05sj3n476","country_code":"JP","type":"education","lineage":["https://openalex.org/I161296585"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yue Wang","raw_affiliation_strings":["Department of Computer Science, School of Information Science and Technology, University of Tokyo, Tokyo, Japan. wangyue@is.s.u-tokyo.ac.jp","Department of Computer Science, School of Information Science and Technology, University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, School of Information Science and Technology, University of Tokyo, Tokyo, Japan. wangyue@is.s.u-tokyo.ac.jp","institution_ids":["https://openalex.org/I161296585"]},{"raw_affiliation_string":"Department of Computer Science, School of Information Science and Technology, University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063923711","display_name":"Jin-Dong Kim","orcid":"https://orcid.org/0000-0001-9660-6303"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jin-Dong Kim","raw_affiliation_strings":["Department of Computer Science, School of Information Science and Technology, University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, School of Information Science and Technology, University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044967495","display_name":"Rune S\u00e6tre","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Rune S\u00e6tre","raw_affiliation_strings":["Department of Computer Science, School of Information Science and Technology, University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, School of Information Science and Technology, University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066925770","display_name":"Sampo Pyysalo","orcid":"https://orcid.org/0000-0002-6279-5000"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sampo Pyysalo","raw_affiliation_strings":["Department of Computer Science, School of Information Science and Technology, University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, School of Information Science and Technology, University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112241147","display_name":"Jun\u2019ichi Tsujii","orcid":null},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]},{"id":"https://openalex.org/I4210112368","display_name":"National Centre for Atmospheric Science","ror":"https://ror.org/01wwwe276","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I141816643","https://openalex.org/I4210087105","https://openalex.org/I4210112368"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["GB","JP"],"is_corresponding":false,"raw_author_name":"Jun'ichi Tsujii","raw_affiliation_strings":["Department of Computer Science, School of Information Science and Technology, University of Tokyo, Tokyo, Japan","National Center for Text Mining, University of Manchester, Manchester, UK","School of Computer Science, University of Manchester, Manchester, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, School of Information Science and Technology, University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"National Center for Text Mining, University of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I4210112368"]},{"raw_affiliation_string":"School of Computer Science, University of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100371984"],"corresponding_institution_ids":["https://openalex.org/I161296585","https://openalex.org/I74801974"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":1.4851,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":{"value":0.8180409,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"10","issue":"1","first_page":"403","last_page":"403"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9434999823570251,"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":0.9434999823570251,"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":0.039400000125169754,"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":0.006099999882280827,"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/computer-science","display_name":"Computer science","score":0.8732448816299438},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.8126736879348755},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.6564191579818726},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.645523726940155},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5787123441696167},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.48362934589385986},{"id":"https://openalex.org/keywords/named-entity","display_name":"Named entity","score":0.46624961495399475},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4385386109352112},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43229764699935913}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8732448816299438},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.8126736879348755},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.6564191579818726},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.645523726940155},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5787123441696167},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.48362934589385986},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.46624961495399475},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4385386109352112},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43229764699935913},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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":[{"descriptor_ui":"D005796","descriptor_name":"Genes","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":false},{"descriptor_ui":"D005796","descriptor_name":"Genes","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":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"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":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"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},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/1471-2105-10-403","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-10-403","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/1471-2105-10-403","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:19995463","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/19995463","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:doaj.org/article:efb4664072a842d9bdfbd1bfc61ff9da","is_oa":false,"landing_page_url":"https://doaj.org/article/efb4664072a842d9bdfbd1bfc61ff9da","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 10, Iss 1, p 403 (2009)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:2804683","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2804683","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:10.1186/1471-2105-10-403","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-10-403","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/1471-2105-10-403","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":[{"id":"https://metadata.un.org/sdg/4","score":0.6399999856948853,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320912","display_name":"Ministry of Education, Culture, Sports, Science and Technology","ror":"https://ror.org/048rj2z13"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2131887446.pdf","grobid_xml":"https://content.openalex.org/works/W2131887446.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1482328859","https://openalex.org/W1487177365","https://openalex.org/W1747861911","https://openalex.org/W1823542770","https://openalex.org/W1932968309","https://openalex.org/W1968848598","https://openalex.org/W1981276685","https://openalex.org/W1995945562","https://openalex.org/W2047782770","https://openalex.org/W2048140075","https://openalex.org/W2057399676","https://openalex.org/W2058412233","https://openalex.org/W2058856481","https://openalex.org/W2061327015","https://openalex.org/W2070786957","https://openalex.org/W2091803989","https://openalex.org/W2102419107","https://openalex.org/W2112670696","https://openalex.org/W2120253533","https://openalex.org/W2120354757","https://openalex.org/W2121844933","https://openalex.org/W2126276057","https://openalex.org/W2134769633","https://openalex.org/W2151698208","https://openalex.org/W2156515921","https://openalex.org/W2157762168","https://openalex.org/W2163107094","https://openalex.org/W2163362093","https://openalex.org/W2166474856","https://openalex.org/W2168905447","https://openalex.org/W2607354300","https://openalex.org/W2793828080","https://openalex.org/W2989631226","https://openalex.org/W2990138404","https://openalex.org/W3082731548","https://openalex.org/W3106889297","https://openalex.org/W4230980737"],"related_works":["https://openalex.org/W2032007337","https://openalex.org/W4377865234","https://openalex.org/W2186562580","https://openalex.org/W2078793151","https://openalex.org/W2155874911","https://openalex.org/W1884363728","https://openalex.org/W4390279576","https://openalex.org/W3128216712","https://openalex.org/W3005759282","https://openalex.org/W3017222382"],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1],"number":[2,242],"of":[3,6,15,22,72,111,127,169,190,221,233,243,262,287,290,294,300,311,347,363,366],"corpora,":[4,354],"collections":[5],"structured":[7],"texts,":[8],"has":[9],"been":[10,37],"increasing,":[11],"as":[12,95,100],"a":[13,86,109,241,260,360],"result":[14,232],"the":[16,20,45,59,70,82,115,124,147,150,156,167,179,198,209,222,227,231,251,256,271,277,281,285,288,292,298,312,320,328,336,348,351,364,373],"growing":[17],"interest":[18,112],"in":[19,44,118,149,195,270,276,350],"application":[21,88],"natural":[23],"language":[24],"processing":[25],"methods":[26],"to":[27,68,93,113,343,359],"biological":[28],"texts.":[29],"Many":[30],"named":[31,55],"entity":[32,56],"recognition":[33],"(NER)":[34],"systems":[35,73],"have":[36],"developed":[38,74],"based":[39,371],"on":[40,75,172,372],"these":[41,119,247],"corpora.":[42,228,339,374],"However,":[43],"biomedical":[46],"community,":[47],"there":[48],"is":[49,66,91,104],"yet":[50],"no":[51],"general":[52],"consensus":[53],"regarding":[54],"annotation;":[57],"thus,":[58],"resources":[60,76,99],"are":[61,370],"largely":[62],"incompatible,":[63],"and":[64,131,143,163,214,249,297,331],"it":[65,90,107],"difficult":[67],"compare":[69],"performance":[71,181,199,365],"that":[77,134,178,224,253,268,308,333,369],"were":[78,135],"divergently":[79],"annotated.":[80],"On":[81],"other":[83],"hand,":[84],"from":[85],"practical":[87],"perspective,":[89],"desirable":[92],"utilize":[94],"many":[96],"existing":[97],"annotated":[98,295,303],"possible,":[101],"because":[102],"annotation":[103,283],"costly.":[105],"Thus,":[106],"becomes":[108],"task":[110],"integrate":[114],"heterogeneous":[116,212],"annotations":[117,133,273],"resources.":[120],"RESULTS:":[121],"We":[122,176,305],"explore":[123],"potential":[125],"sources":[126,245],"incompatibility":[128,157,171],"among":[129,226,335],"gene":[130],"protein":[132,173,367],"made":[136],"for":[137,246],"three":[138,352],"common":[139],"corpora:":[140],"GENIA,":[141],"GENETAG":[142],"AIMed.":[144],"To":[145],"show":[146],"inconsistency":[148],"corpora":[151],"annotations,":[152,213],"we":[153,164,237],"first":[154],"tackle":[155],"problem":[158],"caused":[159,207],"by":[160,208,230,258,317],"corpus":[161],"integration,":[162],"quantitatively":[165],"measure":[166],"effect":[168],"this":[170,234],"mention":[174],"recognition.":[175],"find":[177],"F-score":[180],"declines":[182],"tremendously":[183],"when":[184],"training":[185,191],"with":[186,192],"integrated":[187],"data,":[188],"instead":[189],"pure":[193],"data;":[194],"some":[196],"cases,":[197],"drops":[200],"nearly":[201],"12%.":[202],"This":[203,340],"degradation":[204],"may":[205],"be":[206,216,315],"newly":[210],"added":[211],"cannot":[215],"fixed":[217],"without":[218],"an":[219],"understanding":[220,346,362],"heterogeneities":[223],"exist":[225,274,334],"Motivated":[229],"preliminary":[235],"experiment,":[236],"further":[238,306],"qualitatively":[239],"analyze":[240],"possible":[244],"differences,":[248],"investigate":[250],"factors":[252],"would":[254],"explain":[255],"inconsistencies,":[257],"performing":[259],"series":[261],"well-designed":[263],"experiments.":[264],"Our":[265,325],"analyses":[266],"indicate":[267],"incompatibilities":[269,313],"gene/protein":[272,338],"mainly":[275],"following":[278],"four":[279,321],"areas:":[280],"boundary":[282],"conventions,":[284],"scope":[286],"entities":[289],"interest,":[291],"distribution":[293],"entities,":[296],"ratio":[299],"overlap":[301],"between":[302],"entities.":[304],"suggest":[307],"almost":[309],"all":[310],"can":[314,356],"prevented":[316],"properly":[318],"considering":[319],"aspects":[322],"aforementioned.":[323],"CONCLUSION:":[324],"analysis":[326],"covers":[327],"key":[329],"similarities":[330],"dissimilarities":[332],"diverse":[337],"paper":[341],"serves":[342],"improve":[344],"our":[345],"differences":[349],"studied":[353],"which":[355],"then":[357],"lead":[358],"better":[361],"recognizers":[368]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2025-10-10T00:00:00"}
