{"id":"https://openalex.org/W65830449","doi":null,"title":"A Joint Model for Normalizing Gene and Organism Mentions in Text","display_name":"A Joint Model for Normalizing Gene and Organism Mentions in Text","publication_year":2012,"publication_date":"2012-05-24","ids":{"openalex":"https://openalex.org/W65830449","mag":"65830449"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.229.36","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.229.36","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aclweb.org/anthology/W/W09/W09-4503.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5001436794","display_name":"Georgi Georgiev","orcid":"https://orcid.org/0009-0005-4377-9231","observed_orcids":["https://orcid.org/0009-0005-4377-9231"]},"institutions":[{"id":"https://openalex.org/I46831270","display_name":"Ontotext (Bulgaria)","ror":"https://ror.org/048zn2n32","country_code":"BG","type":"company","lineage":["https://openalex.org/I4405260416","https://openalex.org/I46831270"]}],"countries":["BG"],"is_corresponding":false,"raw_author_name":"Georgi Georgiev","raw_affiliation_strings":["Ontotext AD, Sofia, Bulgaria#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ontotext AD, Sofia, Bulgaria#TAB#","institution_ids":["https://openalex.org/I46831270"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074353028","display_name":"Deyan Peychev","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Deyan Peychev","raw_affiliation_strings":["Nat. Univ. of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nat. Univ. of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5150773068","display_name":"Preslav Nakov","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Preslav Nakov","raw_affiliation_strings":["Univ. of Pennsylvania, Philadelphia, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Pennsylvania, Philadelphia, PA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081573359","display_name":"Kuzman Ganchev","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I46831270","display_name":"Ontotext (Bulgaria)","ror":"https://ror.org/048zn2n32","country_code":"BG","type":"company","lineage":["https://openalex.org/I4405260416","https://openalex.org/I46831270"]}],"countries":["BG"],"is_corresponding":false,"raw_author_name":"Kuzman Ganchev","raw_affiliation_strings":["Ontotext AD, Sofia, Bulgaria#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ontotext AD, Sofia, Bulgaria#TAB#","institution_ids":["https://openalex.org/I46831270"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039455487","display_name":"Vassil Momtchev","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I46831270","display_name":"Ontotext (Bulgaria)","ror":"https://ror.org/048zn2n32","country_code":"BG","type":"company","lineage":["https://openalex.org/I4405260416","https://openalex.org/I46831270"]}],"countries":["BG"],"is_corresponding":false,"raw_author_name":"Vassil Momchev","raw_affiliation_strings":["Ontotext AD, Sofia, Bulgaria#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ontotext AD, Sofia, Bulgaria#TAB#","institution_ids":["https://openalex.org/I46831270"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00487329,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":1.0,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":1.0,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.0,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.0,"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/gene-identifiers","display_name":"gene identifiers","score":0.5350000262260437},{"id":"https://openalex.org/keywords/biomedical-text-mining","display_name":"biomedical text mining","score":0.4390000104904175},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"named entity recognition","score":0.5210000276565552}],"concepts":[{"id":"https://openalex.org/C137858568","wikidata":"https://www.wikidata.org/wiki/Q7239","display_name":"Organism","level":2,"score":0.7544536590576172},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6822506785392761},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.5853090286254883},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5635358095169067},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.527955174446106},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4655839502811432},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.42023614048957825},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41641002893447876},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35393810272216797},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1929548680782318},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.15084800124168396},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.11708205938339233},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.229.36","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.229.36","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.aclweb.org/anthology/W/W09/W09-4503.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1623072288","https://openalex.org/W1979711143","https://openalex.org/W2009190245","https://openalex.org/W2014362743","https://openalex.org/W2040870580","https://openalex.org/W2044602212","https://openalex.org/W2061166439","https://openalex.org/W2096175520","https://openalex.org/W2113040794","https://openalex.org/W2116410915","https://openalex.org/W2125838338","https://openalex.org/W2128600649","https://openalex.org/W2129113459","https://openalex.org/W2139193890","https://openalex.org/W2141150033","https://openalex.org/W2141869602","https://openalex.org/W2147880316","https://openalex.org/W2151296343","https://openalex.org/W2160218441","https://openalex.org/W2167895352"],"related_works":["https://openalex.org/W7096985600","https://openalex.org/W2101265630","https://openalex.org/W2060942759","https://openalex.org/W2007450471","https://openalex.org/W7100999031","https://openalex.org/W7095372244","https://openalex.org/W2113040794","https://openalex.org/W7097981637","https://openalex.org/W4387934104","https://openalex.org/W1590479039"],"abstract_inverted_index":{"The":[0,34,132],"aim":[1],"of":[2,32,40,128,142,149],"gene":[3,22,25,70,92],"mention":[4,52,71],"normalization":[5,96],"is":[6,72,80],"to":[7,65,75,104],"propose":[8],"an":[9,14],"appropriate":[10],"canonical":[11],"name,":[12],"or":[13,23],"identifier":[15],"from":[16,101],"a":[17,21,24,29,38,88],"popular":[18],"database,":[19],"for":[20,43,91,99,135],"product":[26],"mentioned":[27],"in":[28],"given":[30],"piece":[31],"text.":[33],"task":[35,64,86],"has":[36],"attracted":[37],"lot":[39],"research":[41],"attention":[42],"several":[44],"organisms":[45,103],"under":[46],"the":[47,51,55,63,69,77,129,147,150],"assumption":[48],"that":[49],"both":[50],"boundaries":[53],"and":[54,74,93,121],"target":[56],"organism":[57,78,94],"are":[58],"known.":[59],"Here":[60],"we":[61],"extend":[62],"also":[66],"recognizing":[67],"whether":[68],"valid":[73],"finding":[76],"it":[79],"from.":[81],"We":[82],"solve":[83],"this":[84],"extended":[85],"using":[87],"joint":[89,137],"model":[90],"name":[95],"which":[97,145],"allows":[98],"instances":[100],"different":[102,113],"share":[105],"features,":[106],"thus":[107],"achieving":[108],"sizable":[109],"performance":[110],"gains":[111],"with":[112],"learning":[114],"methods:":[115],"Na\u00efve":[116],"Bayes,":[117],"Maximum":[118],"Entropy,":[119],"Perceptron":[120],"mira,":[122],"as":[123,125],"well":[124],"averaged":[126],"versions":[127],"last":[130],"two.":[131],"evaluation":[133],"results":[134],"our":[136],"classifier":[138],"show":[139],"F1":[140],"score":[141],"over":[143],"97%,":[144],"proves":[146],"potential":[148],"approach.":[151]},"counts_by_year":[],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2016-06-24T00:00:00"}