{"id":"https://openalex.org/W2137215472","doi":"https://doi.org/10.1109/icdim.2008.4746791","title":"Identifying bioentity recognition errors of rule-based text-mining systems","display_name":"Identifying bioentity recognition errors of rule-based text-mining systems","publication_year":2008,"publication_date":"2008-11-01","ids":{"openalex":"https://openalex.org/W2137215472","doi":"https://doi.org/10.1109/icdim.2008.4746791","mag":"2137215472"},"language":"en","primary_location":{"id":"doi:10.1109/icdim.2008.4746791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdim.2008.4746791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 Third International Conference on Digital Information Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10451/15001","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014333753","display_name":"Francisco M. Couto","orcid":"https://orcid.org/0000-0003-0627-1496"},"institutions":[{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Francisco M. Couto","raw_affiliation_strings":["Faculty of Sciences, University of Lisbon, Portugal","Fac. of Sci., Univ. of Lisbon, Lisbon"],"affiliations":[{"raw_affiliation_string":"Faculty of Sciences, University of Lisbon, Portugal","institution_ids":["https://openalex.org/I141596103"]},{"raw_affiliation_string":"Fac. of Sci., Univ. of Lisbon, Lisbon","institution_ids":["https://openalex.org/I141596103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060337101","display_name":"Tiago Grego","orcid":"https://orcid.org/0000-0002-7946-7062"},"institutions":[{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Tiago Grego","raw_affiliation_strings":["Faculty of Sciences, University of Lisbon, Portugal","Fac. of Sci., Univ. of Lisbon, Lisbon"],"affiliations":[{"raw_affiliation_string":"Faculty of Sciences, University of Lisbon, Portugal","institution_ids":["https://openalex.org/I141596103"]},{"raw_affiliation_string":"Fac. of Sci., Univ. of Lisbon, Lisbon","institution_ids":["https://openalex.org/I141596103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073297912","display_name":"Hugo Bastos","orcid":"https://orcid.org/0000-0002-8072-4070"},"institutions":[{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Hugo P. Bastos","raw_affiliation_strings":["Faculty of Sciences, University of Lisbon, Portugal","Fac. of Sci., Univ. of Lisbon, Lisbon"],"affiliations":[{"raw_affiliation_string":"Faculty of Sciences, University of Lisbon, Portugal","institution_ids":["https://openalex.org/I141596103"]},{"raw_affiliation_string":"Fac. of Sci., Univ. of Lisbon, Lisbon","institution_ids":["https://openalex.org/I141596103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034898355","display_name":"C\u00e1tia Pesquita","orcid":"https://orcid.org/0000-0002-1847-9393"},"institutions":[{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Catia Pesquita","raw_affiliation_strings":["Faculty of Sciences, University of Lisbon, Portugal","Fac. of Sci., Univ. of Lisbon, Lisbon"],"affiliations":[{"raw_affiliation_string":"Faculty of Sciences, University of Lisbon, Portugal","institution_ids":["https://openalex.org/I141596103"]},{"raw_affiliation_string":"Fac. of Sci., Univ. of Lisbon, Lisbon","institution_ids":["https://openalex.org/I141596103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054446075","display_name":"Rafael Torres","orcid":"https://orcid.org/0000-0002-5739-4413"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rafael Torres","raw_affiliation_strings":["Bioalma SL, Madrid, Spain","Bioalma SL, Tres Cantos"],"affiliations":[{"raw_affiliation_string":"Bioalma SL, Madrid, Spain","institution_ids":[]},{"raw_affiliation_string":"Bioalma SL, Tres Cantos","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103381359","display_name":"Pablo Huertas S\u00e1nchez","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pablo Sanchez","raw_affiliation_strings":["Bioalma SL, Madrid, Spain","Bioalma SL, Tres Cantos"],"affiliations":[{"raw_affiliation_string":"Bioalma SL, Madrid, Spain","institution_ids":[]},{"raw_affiliation_string":"Bioalma SL, Tres Cantos","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109860990","display_name":"Leandro Pascual","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leandro Pascual","raw_affiliation_strings":["Bioalma SL, Madrid, Spain","Bioalma SL, Tres Cantos"],"affiliations":[{"raw_affiliation_string":"Bioalma SL, Madrid, Spain","institution_ids":[]},{"raw_affiliation_string":"Bioalma SL, Tres Cantos","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017361070","display_name":"Christian Blaschke","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christian Blaschke","raw_affiliation_strings":["Bioalma SL, Madrid, Spain","Bioalma SL, Tres Cantos"],"affiliations":[{"raw_affiliation_string":"Bioalma SL, Madrid, Spain","institution_ids":[]},{"raw_affiliation_string":"Bioalma SL, Tres Cantos","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5014333753"],"corresponding_institution_ids":["https://openalex.org/I141596103"],"apc_list":null,"apc_paid":null,"fwci":0.1383,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.56220884,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"733","last_page":"738"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9998999834060669,"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":0.9998999834060669,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9775999784469604,"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/T10028","display_name":"Topic Modeling","score":0.9397000074386597,"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/annotation","display_name":"Annotation","score":0.7961951494216919},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7756954431533813},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.6881577968597412},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6476900577545166},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.48990315198898315},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4888969957828522},{"id":"https://openalex.org/keywords/biomedical-text-mining","display_name":"Biomedical text mining","score":0.48542293906211853},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.406574547290802},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4029293358325958},{"id":"https://openalex.org/keywords/text-mining","display_name":"Text mining","score":0.3748416602611542},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.09433102607727051},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.0731530487537384}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7961951494216919},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7756954431533813},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.6881577968597412},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6476900577545166},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.48990315198898315},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4888969957828522},{"id":"https://openalex.org/C165141518","wikidata":"https://www.wikidata.org/wiki/Q4915126","display_name":"Biomedical text mining","level":3,"score":0.48542293906211853},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.406574547290802},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4029293358325958},{"id":"https://openalex.org/C71472368","wikidata":"https://www.wikidata.org/wiki/Q676880","display_name":"Text mining","level":2,"score":0.3748416602611542},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.09433102607727051},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0731530487537384},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icdim.2008.4746791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdim.2008.4746791","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 Third International Conference on Digital Information Management","raw_type":"proceedings-article"},{"id":"pmh:oai:repositorio.ul.pt:10451/15001","is_oa":true,"landing_page_url":"http://hdl.handle.net/10451/15001","pdf_url":null,"source":{"id":"https://openalex.org/S4306402433","display_name":"Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"}],"best_oa_location":{"id":"pmh:oai:repositorio.ul.pt:10451/15001","is_oa":true,"landing_page_url":"http://hdl.handle.net/10451/15001","pdf_url":null,"source":{"id":"https://openalex.org/S4306402433","display_name":"Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT)","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"},"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1535407053","https://openalex.org/W1575522899","https://openalex.org/W1976097579","https://openalex.org/W2011295095","https://openalex.org/W2014849717","https://openalex.org/W2044420612","https://openalex.org/W2061327015","https://openalex.org/W2097106271","https://openalex.org/W2123273303","https://openalex.org/W2124617249","https://openalex.org/W2126276057","https://openalex.org/W2141150033","https://openalex.org/W2151598682","https://openalex.org/W2152183901","https://openalex.org/W2917056928","https://openalex.org/W2917293077","https://openalex.org/W6631832797","https://openalex.org/W6678356393"],"related_works":["https://openalex.org/W3185751515","https://openalex.org/W1479703980","https://openalex.org/W2749535755","https://openalex.org/W1553529581","https://openalex.org/W4206039273","https://openalex.org/W4232119327","https://openalex.org/W2911489562","https://openalex.org/W2134429551","https://openalex.org/W3183808544","https://openalex.org/W2188854577"],"abstract_inverted_index":{"An":[0],"important":[1],"research":[2],"topic":[3],"in":[4,37,58,86,111,221],"Bioinformatics":[5],"involves":[6],"the":[7,20,32,55,125,179,217],"exploration":[8],"of":[9,12,73,119,132,134,153,160,219],"vast":[10],"amounts":[11],"biological":[13],"and":[14,53,192],"biomedical":[15],"scientific":[16],"literature":[17],"(BioLiterature).":[18],"Over":[19],"last":[21],"few":[22],"decades,":[23],"text-mining":[24],"systems":[25,106],"have":[26],"exploited":[27],"this":[28],"BioLiterature":[29],"to":[30,123,143,199],"reduce":[31],"time":[33],"spent":[34],"by":[35,51,104,167,183],"researchers":[36],"its":[38],"analysis.":[39],"However,":[40],"state-of-the-art":[41,171],"approaches":[42],"are":[43,140],"still":[44],"far":[45],"from":[46],"reaching":[47],"performance":[48,56],"levels":[49,72],"acceptable":[50],"curators,":[52],"below":[54],"obtained":[57],"other":[59],"domains,":[60],"such":[61],"as":[62,189],"personal":[63],"name":[64,173],"recognition":[65,175],"or":[66],"news":[67],"text.":[68],"To":[69],"achieve":[70],"high":[71],"performance,":[74],"it":[75],"is":[76],"essential":[77],"that":[78,107,128,186,195],"text":[79],"mining":[80],"tools":[81],"effectively":[82],"recognize":[83,109],"bioentities":[84,110],"present":[85],"BioLiterature.":[87,112],"This":[88],"paper":[89],"presents":[90],"FIBRE":[91,113,154,187,196,220],"(Filtering":[92],"Bioentity":[93],"Recognition":[94],"Errors),":[95],"a":[96,135,148,158,170,202,222],"system":[97],"for":[98],"automatically":[99,108,120],"filtering":[100],"mis":[101,145,209],"annotations":[102,122,146,181],"generated":[103,121],"rule-based":[105,172],"aims":[114],"at":[115],"using":[116,147],"different":[117],"sets":[118],"identify":[124],"main":[126],"features":[127,139],"characterize":[129],"an":[130],"annotation":[131],"being":[133],"certain":[136],"type.":[137],"These":[138],"then":[141],"used":[142],"filter":[144,200],"confidence":[149],"threshold.":[150],"The":[151],"assessment":[152],"was":[155,197],"performed":[156],"on":[157],"set":[159],"more":[161,206],"than":[162,207],"17,000":[163],"documents,":[164],"previously":[165],"annotated":[166],"Text":[168,184],"Detective,":[169],"bioentity":[174],"system.":[176],"Curators":[177],"evaluated":[178],"gene":[180],"given":[182],"Detective":[185],"classified":[188],"non-gene":[190],"annotations,":[191,210],"we":[193],"found":[194],"able":[198],"with":[201],"precision":[203],"above":[204],"92%":[205],"600":[208],"requiring":[211],"minimal":[212],"human":[213],"effort,":[214],"which":[215],"demonstrates":[216],"effectiveness":[218],"realistic":[223],"scenario.":[224]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}