{"id":"https://openalex.org/W1997201617","doi":"https://doi.org/10.5402/2012/619427","title":"Chemical Entity Recognition and Resolution to ChEBI","display_name":"Chemical Entity Recognition and Resolution to ChEBI","publication_year":2012,"publication_date":"2012-02-15","ids":{"openalex":"https://openalex.org/W1997201617","doi":"https://doi.org/10.5402/2012/619427","mag":"1997201617","pmid":"https://pubmed.ncbi.nlm.nih.gov/25937941"},"language":"en","primary_location":{"id":"doi:10.5402/2012/619427","doi":"https://doi.org/10.5402/2012/619427","is_oa":true,"landing_page_url":"https://doi.org/10.5402/2012/619427","pdf_url":"https://downloads.hindawi.com/archive/2012/619427.pdf","source":{"id":"https://openalex.org/S4210183111","display_name":"ISRN Bioinformatics","issn_l":"2090-7338","issn":["2090-7338","2090-7346"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869","https://openalex.org/P4310320595"],"host_organization_lineage_names":["Hindawi Publishing Corporation","Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ISRN Bioinformatics","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://downloads.hindawi.com/archive/2012/619427.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060337101","display_name":"Tiago Grego","orcid":"https://orcid.org/0000-0002-7946-7062","observed_orcids":["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":true,"raw_author_name":"Tiago Grego","raw_affiliation_strings":["Departamento de Inform\u00e1tica, Faculdade de Ci\u00eancias, Universidade de Lisboa, 1749-016 Lisboa, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departamento de Inform\u00e1tica, Faculdade de Ci\u00eancias, Universidade de Lisboa, 1749-016 Lisboa, Portugal","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","observed_orcids":["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":["Departamento de Inform\u00e1tica, Faculdade de Ci\u00eancias, Universidade de Lisboa, 1749-016 Lisboa, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departamento de Inform\u00e1tica, Faculdade de Ci\u00eancias, Universidade de Lisboa, 1749-016 Lisboa, Portugal","institution_ids":["https://openalex.org/I141596103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073297912","display_name":"Hugo P. Bastos","orcid":"https://orcid.org/0000-0002-8072-4070","observed_orcids":["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":["Departamento de Inform\u00e1tica, Faculdade de Ci\u00eancias, Universidade de Lisboa, 1749-016 Lisboa, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departamento de Inform\u00e1tica, Faculdade de Ci\u00eancias, Universidade de Lisboa, 1749-016 Lisboa, Portugal","institution_ids":["https://openalex.org/I141596103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014333753","display_name":"Francisco M. Couto","orcid":"https://orcid.org/0000-0003-0627-1496","observed_orcids":["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":false,"raw_author_name":"Francisco M. Couto","raw_affiliation_strings":["Departamento de Inform\u00e1tica, Faculdade de Ci\u00eancias, Universidade de Lisboa, 1749-016 Lisboa, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Departamento de Inform\u00e1tica, Faculdade de Ci\u00eancias, Universidade de Lisboa, 1749-016 Lisboa, Portugal","institution_ids":["https://openalex.org/I141596103"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5060337101"],"corresponding_institution_ids":["https://openalex.org/I141596103"],"apc_list":null,"apc_paid":null,"fwci":1.8581,"has_fulltext":true,"cited_by_count":28,"citation_normalized_percentile":{"value":0.84879924,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":"2012","issue":null,"first_page":"1","last_page":"9"},"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/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":1.0,"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/T10215","display_name":"Semantic Web and Ontologies","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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/chemical-entity-recognition","display_name":"chemical entity recognition","score":0.9869999885559082},{"id":"https://openalex.org/keywords/chebi","display_name":"ChEBI","score":0.9900000095367432},{"id":"https://openalex.org/keywords/biomedical-text-mining","display_name":"biomedical text mining","score":0.7450000047683716},{"id":"https://openalex.org/keywords/word-similarity","display_name":"word similarity","score":0.796999990940094},{"id":"https://openalex.org/keywords/annotated-corpora","display_name":"annotated corpus","score":0.578000009059906},{"id":"https://openalex.org/keywords/chemical-named-entity-recognition","display_name":"chemical named entity recognition","score":0.4909999966621399}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4134387671947479},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3896089196205139},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.163825124502182}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.5402/2012/619427","doi":"https://doi.org/10.5402/2012/619427","is_oa":true,"landing_page_url":"https://doi.org/10.5402/2012/619427","pdf_url":"https://downloads.hindawi.com/archive/2012/619427.pdf","source":{"id":"https://openalex.org/S4210183111","display_name":"ISRN Bioinformatics","issn_l":"2090-7338","issn":["2090-7338","2090-7346"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869","https://openalex.org/P4310320595"],"host_organization_lineage_names":["Hindawi Publishing Corporation","Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ISRN Bioinformatics","raw_type":"journal-article"},{"id":"pmid:25937941","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/25937941","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,"listed_in":[],"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":"ISRN bioinformatics","raw_type":"Journal Article"},{"id":"pmh:oai:europepmc.org:3382237","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4393067","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":null,"raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:4393067","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4393067","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,"listed_in":[],"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":"ISRN Bioinform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.5402/2012/619427","doi":"https://doi.org/10.5402/2012/619427","is_oa":true,"landing_page_url":"https://doi.org/10.5402/2012/619427","pdf_url":"https://downloads.hindawi.com/archive/2012/619427.pdf","source":{"id":"https://openalex.org/S4210183111","display_name":"ISRN Bioinformatics","issn_l":"2090-7338","issn":["2090-7338","2090-7346"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869","https://openalex.org/P4310320595"],"host_organization_lineage_names":["Hindawi Publishing Corporation","Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ISRN Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality education","score":0.6299999952316284}],"study_designs":[],"awards":[{"id":"https://openalex.org/G3798724212","display_name":"VALIDA\u00c7\u00c3O E GERA\u00c7\u00c3O AUTOM\u00c1TICA DE ANOTA\u00c7\u00d5ES DE PROTE\u00cdNAS COM BASE NA SUA CLASSIFICA\u00c7\u00c3O EM FAM\u00cdLIAS","funder_award_id":"SFRH/BD/48035/2008","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G6061418153","display_name":"EXTENS\u00c3O E ENRIQUECIMENTO AUTOMATIZADO DE BIOONTOLOGIAS","funder_award_id":"SFRH/BD/42481/2007","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G7967794104","display_name":"Developing the Framework for an Epidemic Forecast Infrastructure","funder_award_id":"231807","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334779","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","ror":"https://ror.org/00snfqn58"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1997201617.pdf","grobid_xml":"https://content.openalex.org/works/W1997201617.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W198996565","https://openalex.org/W1490056294","https://openalex.org/W1747861911","https://openalex.org/W2008085355","https://openalex.org/W2015809202","https://openalex.org/W2033377040","https://openalex.org/W2039612385","https://openalex.org/W2047782770","https://openalex.org/W2049240985","https://openalex.org/W2095596879","https://openalex.org/W2099100406","https://openalex.org/W2099369363","https://openalex.org/W2113079146","https://openalex.org/W2114453188","https://openalex.org/W2115964835","https://openalex.org/W2124834853","https://openalex.org/W2126276057","https://openalex.org/W2127239015","https://openalex.org/W2127603354","https://openalex.org/W2129113459","https://openalex.org/W2138689719","https://openalex.org/W2140407633","https://openalex.org/W2142741334","https://openalex.org/W2144949988","https://openalex.org/W2154142897"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Chemical":[0],"entities":[1,19],"are":[2,20],"ubiquitous":[3],"through":[4],"the":[5,9,24,32,39,51,56,95,109,115],"biomedical":[6],"literature":[7],"and":[8,29,43,55,76,84,118,124],"development":[10,40],"of":[11,26,41,53,58,106],"text-mining":[12],"systems":[13],"that":[14],"can":[15,64],"efficiently":[16],"identify":[17],"those":[18],"required.":[21],"Due":[22],"to":[23],"lack":[25],"available":[27],"corpora":[28],"data":[30],"resources,":[31],"community":[33],"has":[34],"focused":[35],"its":[36],"efforts":[37],"in":[38,98,104],"gene":[42],"protein":[44],"named":[45],"entity":[46,74,82,110,122],"recognition":[47,75,111,123],"systems,":[48],"but":[49],"with":[50,87],"release":[52],"ChEBI":[54],"availability":[57],"an":[59,102],"annotated":[60],"corpus,":[61],"this":[62],"task":[63],"be":[65],"addressed.":[66],"We":[67],"developed":[68],"a":[69,77,89],"machine-learning-based":[70],"method":[71,79,97],"for":[72,80,108,114,120],"chemical":[73,81],"lexical-similarity-based":[78],"resolution":[83,125],"compared":[85],"them":[86],"Whatizit,":[88],"popular-dictionary-based":[90],"method.":[91],"Our":[92],"methods":[93],"outperformed":[94],"dictionary-based":[96],"all":[99],"tasks,":[100],"yielding":[101],"improvement":[103],"F-measure":[105],"20%":[107],"task,":[112,117],"2-5%":[113],"entity-resolution":[116],"15%":[119],"combined":[121],"tasks.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}