{"id":"https://openalex.org/W2152966407","doi":"https://doi.org/10.1093/database/bau044","title":"Finding abbreviations in biomedical literature: three BioC-compatible modules and four BioC-formatted corpora","display_name":"Finding abbreviations in biomedical literature: three BioC-compatible modules and four BioC-formatted corpora","publication_year":2014,"publication_date":"2014-06-09","ids":{"openalex":"https://openalex.org/W2152966407","doi":"https://doi.org/10.1093/database/bau044","mag":"2152966407","pmid":"https://pubmed.ncbi.nlm.nih.gov/24914232"},"language":"en","primary_location":{"id":"doi:10.1093/database/bau044","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/bau044","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/bau044/8245883/bau044.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/bau044/8245883/bau044.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"R. Islamaj Do\u00a0an","orcid":null},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"R. Islamaj Do\u00a0an","raw_affiliation_strings":["National Center for Biotechnology Information, U.S. National Library of Medicine, National Institutes of Health, 8600 Rockville Pike, Bethesda, MD 20894, USA"],"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, U.S. National Library of Medicine, National Institutes of Health, 8600 Rockville Pike, Bethesda, MD 20894, USA","institution_ids":["https://openalex.org/I4210109390","https://openalex.org/I1299303238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111968060","display_name":"D. C. Comeau","orcid":null},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D. C. Comeau","raw_affiliation_strings":["National Center for Biotechnology Information, U.S. National Library of Medicine, National Institutes of Health, 8600 Rockville Pike, Bethesda, MD 20894, USA"],"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, U.S. National Library of Medicine, National Institutes of Health, 8600 Rockville Pike, Bethesda, MD 20894, USA","institution_ids":["https://openalex.org/I4210109390","https://openalex.org/I1299303238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002159664","display_name":"Lana Yeganova","orcid":"https://orcid.org/0000-0001-9527-0764"},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"L. Yeganova","raw_affiliation_strings":["National Center for Biotechnology Information, U.S. National Library of Medicine, National Institutes of Health, 8600 Rockville Pike, Bethesda, MD 20894, USA"],"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, U.S. National Library of Medicine, National Institutes of Health, 8600 Rockville Pike, Bethesda, MD 20894, USA","institution_ids":["https://openalex.org/I4210109390","https://openalex.org/I1299303238"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111895206","display_name":"W. John Wilbur","orcid":null},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4210109390","display_name":"National Center for Biotechnology Information","ror":"https://ror.org/02meqm098","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I2800548410","https://openalex.org/I4210109390"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"W. J. Wilbur","raw_affiliation_strings":["National Center for Biotechnology Information, U.S. National Library of Medicine, National Institutes of Health, 8600 Rockville Pike, Bethesda, MD 20894, USA"],"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, U.S. National Library of Medicine, National Institutes of Health, 8600 Rockville Pike, Bethesda, MD 20894, USA","institution_ids":["https://openalex.org/I4210109390","https://openalex.org/I1299303238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4210109390"],"apc_list":{"value":1415,"currency":"GBP","value_usd":1735},"apc_paid":{"value":1415,"currency":"GBP","value_usd":1735},"fwci":1.5687,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.83093393,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"2014","issue":"0","first_page":"bau044","last_page":"bau044"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9951000213623047,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9922000169754028,"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":0.6933825016021729},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5436022877693176},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5358096361160278},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43523216247558594},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.34734901785850525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6933825016021729},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5436022877693176},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5358096361160278},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43523216247558594},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.34734901785850525}],"mesh":[{"descriptor_ui":"D000004","descriptor_name":"Abbreviations as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000004","descriptor_name":"Abbreviations as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000004","descriptor_name":"Abbreviations as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064229","descriptor_name":"Biological Ontologies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064229","descriptor_name":"Biological Ontologies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064229","descriptor_name":"Biological Ontologies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/database/bau044","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/bau044","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/bau044/8245883/bau044.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},{"id":"pmid:24914232","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/24914232","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":"Database : the journal of biological databases and curation","raw_type":null},{"id":"pmh:oai:europepmc.org:3028701","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4051513","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,"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/database/bau044","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/bau044","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/bau044/8245883/bau044.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2152966407.pdf","grobid_xml":"https://content.openalex.org/works/W2152966407.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W116705248","https://openalex.org/W1991154713","https://openalex.org/W2020357318","https://openalex.org/W2024940313","https://openalex.org/W2061167720","https://openalex.org/W2101727078","https://openalex.org/W2104148262","https://openalex.org/W2126276057","https://openalex.org/W2152398020","https://openalex.org/W2161132397","https://openalex.org/W2163303745","https://openalex.org/W2166817943","https://openalex.org/W2555756618"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W1596801655","https://openalex.org/W3204019825"],"abstract_inverted_index":{"BioC":[0,38,67,226],"is":[1],"a":[2,41,206],"recently":[3],"created":[4],"XML":[5],"format":[6],"to":[7,18,39,69,154,167],"share":[8],"text":[9,47],"data":[10,22,219],"and":[11,13,23,62,83,122,125,142,145,156,173,218],"annotations,":[12],"an":[14],"accompanying":[15],"input/output":[16],"library":[17],"promote":[19],"interoperability":[20],"of":[21,29,37,49,95,103,110,118,128,160],"tools":[24],"for":[25,210,222],"natural":[26],"language":[27],"processing":[28,45],"biomedical":[30,46,98],"text.":[31],"This":[32],"article":[33],"reports":[34],"the":[35,64,100,107,114,123,158,161,169,174,225],"use":[36],"address":[40],"common":[42,207],"challenge":[43],"in":[44,97,133,190],"information-that":[48],"frequent":[50],"entity":[51],"name":[52],"abbreviation.":[53],"We":[54,151],"selected":[55],"three":[56,170],"different":[57],"abbreviation":[58],"definition":[59],"identification":[60],"modules,":[61,180],"used":[63,166,204],"publicly":[65],"available":[66,221],"code":[68],"convert":[70],"these":[71,134],"independent":[72],"modules":[73],"into":[74],"BioC-compatible":[75,85,179],"components":[76],"that":[77],"interact":[78],"seamlessly":[79],"with":[80,183],"BioC-formatted":[81],"data,":[82],"other":[84,197],"modules.":[86],"In":[87],"addition,":[88],"we":[89],"consider":[90],"four":[91,140],"manually":[92],"annotated":[93],"corpora":[94,135,164],"abbreviations":[96],"text:":[99],"Ab3P":[101],"corpus":[102,109,117,127],"1250":[104],"PubMed":[105,112,130],"abstracts,":[106,113],"BIOADI":[108],"1201":[111],"old":[115],"MEDSTRACT":[116],"199":[119],"PubMed(\u00ae)":[120],"citations":[121],"Schwartz":[124],"Hearst":[126],"1000":[129],"abstracts.":[131],"Annotations":[132],"have":[136,148,187],"been":[137,149],"re-evaluated":[138],"by":[139],"annotators":[141],"their":[143,184,191],"consistency":[144],"quality":[146],"levels":[147],"improved.":[150],"converted":[152],"them":[153],"BioC-format":[155],"described":[157],"representation":[159],"annotations.":[162],"These":[163],"are":[165,176,220],"measure":[168],"abbreviation-finding":[171],"algorithms":[172],"results":[175],"given.":[177],"The":[178],"when":[181],"compared":[182],"original":[185],"form,":[186],"no":[188],"difference":[189],"efficiency,":[192],"running":[193],"time":[194],"or":[195],"any":[196],"comparable":[198],"aspects.":[199],"They":[200],"can":[201],"be":[202],"conveniently":[203],"as":[205],"pre-processing":[208],"step":[209],"larger":[211],"multi-layered":[212],"text-mining":[213],"endeavors.":[214],"Database":[215],"URL:":[216],"Code":[217],"download":[223],"at":[224],"site:":[227],"http://bioc.sourceforge.net.":[228]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2014,"cited_by_count":4}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2016-06-24T00:00:00"}
