{"id":"https://openalex.org/W2020801982","doi":"https://doi.org/10.3115/1118958.1118959","title":"Gene name extraction using FlyBase resources","display_name":"Gene name extraction using FlyBase resources","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W2020801982","doi":"https://doi.org/10.3115/1118958.1118959","mag":"2020801982"},"language":"en","primary_location":{"id":"doi:10.3115/1118958.1118959","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1118958.1118959","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1118958.1118959","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACL 2003 workshop on Natural language processing in biomedicine  -","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.3115/1118958.1118959","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111935828","display_name":"Alex A. Morgan","orcid":"https://orcid.org/0009-0002-7989-0079"},"institutions":[{"id":"https://openalex.org/I44896327","display_name":"Mitre (United States)","ror":"https://ror.org/03ks2a131","country_code":"US","type":"company","lineage":["https://openalex.org/I44896327"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Morgan","raw_affiliation_strings":["The MITRE Corporation, Bedford, MA","The MITRE Corp., Bedford, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The MITRE Corporation, Bedford, MA","institution_ids":["https://openalex.org/I44896327"]},{"raw_affiliation_string":"The MITRE Corp., Bedford, MA","institution_ids":["https://openalex.org/I44896327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068115280","display_name":"Lynette Hirschman","orcid":"https://orcid.org/0000-0001-8442-0720"},"institutions":[{"id":"https://openalex.org/I44896327","display_name":"Mitre (United States)","ror":"https://ror.org/03ks2a131","country_code":"US","type":"company","lineage":["https://openalex.org/I44896327"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lynette Hirschman","raw_affiliation_strings":["The MITRE Corporation, Bedford, MA","The MITRE Corp., Bedford, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The MITRE Corporation, Bedford, MA","institution_ids":["https://openalex.org/I44896327"]},{"raw_affiliation_string":"The MITRE Corp., Bedford, MA","institution_ids":["https://openalex.org/I44896327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109982569","display_name":"Alexander Yeh","orcid":null},"institutions":[{"id":"https://openalex.org/I44896327","display_name":"Mitre (United States)","ror":"https://ror.org/03ks2a131","country_code":"US","type":"company","lineage":["https://openalex.org/I44896327"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Yeh","raw_affiliation_strings":["The MITRE Corporation, Bedford, MA","The MITRE Corp., Bedford, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The MITRE Corporation, Bedford, MA","institution_ids":["https://openalex.org/I44896327"]},{"raw_affiliation_string":"The MITRE Corp., Bedford, MA","institution_ids":["https://openalex.org/I44896327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082822281","display_name":"Marc Colosimo","orcid":null},"institutions":[{"id":"https://openalex.org/I44896327","display_name":"Mitre (United States)","ror":"https://ror.org/03ks2a131","country_code":"US","type":"company","lineage":["https://openalex.org/I44896327"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marc Colosimo","raw_affiliation_strings":["The MITRE Corporation, Bedford, MA","The MITRE Corp., Bedford, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The MITRE Corporation, Bedford, MA","institution_ids":["https://openalex.org/I44896327"]},{"raw_affiliation_string":"The MITRE Corp., Bedford, MA","institution_ids":["https://openalex.org/I44896327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2913,"has_fulltext":true,"cited_by_count":41,"citation_normalized_percentile":{"value":0.87929446,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"13","issue":null,"first_page":"1","last_page":"8"},"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9908999800682068,"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":0.9589999914169312,"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":0.8584269285202026},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7008156180381775},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6388808488845825},{"id":"https://openalex.org/keywords/synonym","display_name":"Synonym (taxonomy)","score":0.5745152831077576},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.5450910925865173},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5298868417739868},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5211608409881592},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5026969909667969},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4720795154571533},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4651993215084076},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4483361840248108},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.445400208234787},{"id":"https://openalex.org/keywords/gene-nomenclature","display_name":"Gene nomenclature","score":0.4386945366859436},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.43637973070144653},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4056296944618225},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.23898354172706604},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.14694178104400635},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08576148748397827}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8584269285202026},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7008156180381775},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6388808488845825},{"id":"https://openalex.org/C173483453","wikidata":"https://www.wikidata.org/wiki/Q1040689","display_name":"Synonym (taxonomy)","level":3,"score":0.5745152831077576},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.5450910925865173},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5298868417739868},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5211608409881592},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5026969909667969},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4720795154571533},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4651993215084076},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4483361840248108},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.445400208234787},{"id":"https://openalex.org/C62177273","wikidata":"https://www.wikidata.org/wiki/Q5531556","display_name":"Gene nomenclature","level":4,"score":0.4386945366859436},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.43637973070144653},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4056296944618225},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.23898354172706604},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.14694178104400635},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08576148748397827},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C157369684","wikidata":"https://www.wikidata.org/wiki/Q34740","display_name":"Genus","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C514705636","wikidata":"https://www.wikidata.org/wiki/Q863247","display_name":"Nomenclature","level":3,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/1118958.1118959","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1118958.1118959","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1118958.1118959","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACL 2003 workshop on Natural language processing in biomedicine  -","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.63.8843","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.63.8843","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acl.ldc.upenn.edu/acl2003/nlbio/pdf/Morgan.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.3115/1118958.1118959","is_oa":true,"landing_page_url":"https://doi.org/10.3115/1118958.1118959","pdf_url":"https://dl.acm.org/doi/pdf/10.3115/1118958.1118959","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACL 2003 workshop on Natural language processing in biomedicine  -","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2020801982.pdf","grobid_xml":"https://content.openalex.org/works/W2020801982.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1520377376","https://openalex.org/W1954715867","https://openalex.org/W2031868269","https://openalex.org/W2032898843","https://openalex.org/W2050006154","https://openalex.org/W2091483147","https://openalex.org/W2097106271","https://openalex.org/W2107804596","https://openalex.org/W2130260860","https://openalex.org/W2134769633","https://openalex.org/W2150650678","https://openalex.org/W2152183901","https://openalex.org/W2167895352","https://openalex.org/W6684737164"],"related_works":["https://openalex.org/W2334378031","https://openalex.org/W2916255597","https://openalex.org/W2999302224","https://openalex.org/W3091569222","https://openalex.org/W4241018868","https://openalex.org/W1495833002","https://openalex.org/W2075635421","https://openalex.org/W2964631078","https://openalex.org/W3160627956","https://openalex.org/W3006227201"],"abstract_inverted_index":{"Machine-learning":[0],"based":[1],"entity":[2,61,142],"extraction":[3,65],"requires":[4],"a":[5,44,59,80,95,127,136],"large":[6,52],"corpus":[7],"of":[8,18,21,27,51,54,83,118,159,166],"annotated":[9],"training":[10,56],"to":[11,35,103,134,152,170],"achieve":[12],"acceptable":[13],"results.":[14],"However,":[15],"the":[16,37,48,72,86,90,108,116,122,147,164],"cost":[17],"expert":[19],"annotation":[20],"relevant":[22],"data,":[23],"coupled":[24],"with":[25],"issues":[26],"inter-annotator":[28],"variability,":[29],"makes":[30],"it":[31],"expensive":[32],"and":[33,85,111],"time-consuming":[34],"create":[36],"necessary":[38],"corpora.":[39],"We":[40,67,98],"report":[41],"here":[42],"on":[43],"simple":[45,100,137],"method":[46,162],"for":[47,58,121],"automatic":[49],"creation":[50],"quantities":[53],"imperfect":[55],"data":[57,128],"biological":[60],"(gene":[62],"or":[63],"protein)":[64],"system.":[66],"used":[68,133],"resources":[69,78],"available":[70],"in":[71,107],"FlyBase":[73],"model":[74],"organism":[75],"database;":[76],"these":[77,113],"include":[79],"curated":[81,119],"lists":[82],"genes":[84],"articles":[87],"from":[88,146],"which":[89],"entries":[91,120],"were":[92,150],"drawn,":[93],"together":[94],"synonym":[96],"lexicon.":[97],"applied":[99],"pattern":[101],"matching":[102],"identify":[104],"gene":[105],"names":[106],"associated":[109],"abstracts":[110],"filtered":[112],"entities":[114],"using":[115],"list":[117],"article.":[123],"This":[124,161],"process":[125],"created":[126],"set":[129],"that":[130,173],"could":[131],"be":[132],"train":[135],"Hidden":[138],"Markov":[139],"Model":[140],"(HMM)":[141],"tagger.":[143],"The":[144],"results":[145],"HMM":[148],"tagger":[149],"comparable":[151],"those":[153],"reported":[154],"by":[155],"other":[156],"groups":[157],"(F-measure":[158],"0.75).":[160],"has":[163],"advantage":[165],"being":[167],"rapidly":[168],"transferable":[169],"new":[171],"domains":[172],"have":[174],"similar":[175],"existing":[176],"resources.":[177]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
