{"id":"https://openalex.org/W2024940313","doi":"https://doi.org/10.1186/1471-2105-12-s3-s6","title":"Machine learning with naturally labeled data for identifying abbreviation definitions","display_name":"Machine learning with naturally labeled data for identifying abbreviation definitions","publication_year":2011,"publication_date":"2011-06-09","ids":{"openalex":"https://openalex.org/W2024940313","doi":"https://doi.org/10.1186/1471-2105-12-s3-s6","mag":"2024940313","pmid":"https://pubmed.ncbi.nlm.nih.gov/21658293"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-12-s3-s6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-12-s3-s6","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-12-S3-S6","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-12-S3-S6","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002159664","display_name":"Lana Yeganova","orcid":"https://orcid.org/0000-0001-9527-0764"},"institutions":[{"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":"Lana Yeganova","raw_affiliation_strings":["National Center for Biotechnology Information, NLM, NIH, Bethesda, MD, USA. yeganova@mail.nih.gov","National Center for Biotechnology Information, NLM, NIH, Bethesda, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, NLM, NIH, Bethesda, MD, USA. yeganova@mail.nih.gov","institution_ids":["https://openalex.org/I4210109390"]},{"raw_affiliation_string":"National Center for Biotechnology Information, NLM, NIH, Bethesda, USA","institution_ids":["https://openalex.org/I4210109390"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031842571","display_name":"Donald C. Comeau","orcid":"https://orcid.org/0000-0002-9373-530X"},"institutions":[{"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":"Donald C Comeau","raw_affiliation_strings":["National Center for Biotechnology Information, NLM, NIH, Bethesda, MD, USA","National Center for Biotechnology Information, NLM, NIH, Bethesda, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, NLM, NIH, Bethesda, MD, USA","institution_ids":["https://openalex.org/I4210109390"]},{"raw_affiliation_string":"National Center for Biotechnology Information, NLM, NIH, Bethesda, USA","institution_ids":["https://openalex.org/I4210109390"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111895206","display_name":"W. John Wilbur","orcid":null},"institutions":[{"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 John Wilbur","raw_affiliation_strings":["National Center for Biotechnology Information, NLM, NIH, Bethesda, MD, USA","National Center for Biotechnology Information, NLM, NIH, Bethesda, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Center for Biotechnology Information, NLM, NIH, Bethesda, MD, USA","institution_ids":["https://openalex.org/I4210109390"]},{"raw_affiliation_string":"National Center for Biotechnology Information, NLM, NIH, Bethesda, USA","institution_ids":["https://openalex.org/I4210109390"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5002159664"],"corresponding_institution_ids":["https://openalex.org/I4210109390"],"apc_list":{"value":2790,"currency":"USD","value_usd":2790},"apc_paid":{"value":2790,"currency":"USD","value_usd":2790},"fwci":1.2169,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.77337396,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"12","issue":"S3","first_page":"S6","last_page":"S6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.98580002784729,"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":0.98580002784729,"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/T13326","display_name":"Biochemical and Structural Characterization","score":0.001500000013038516,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.0008999999845400453,"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":0.8444058895111084},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6677564382553101},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.6465321183204651},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6100090742111206},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5789006352424622},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5692152976989746},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49511805176734924},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.46486005187034607},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46199703216552734},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.4149933159351349},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.41245874762535095},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3424220681190491},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3270754814147949}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8444058895111084},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6677564382553101},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.6465321183204651},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6100090742111206},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5789006352424622},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5692152976989746},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49511805176734924},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.46486005187034607},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46199703216552734},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.4149933159351349},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.41245874762535095},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3424220681190491},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3270754814147949},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"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":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1186/1471-2105-12-s3-s6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-12-s3-s6","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-12-S3-S6","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:21658293","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/21658293","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:3111592","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3111592","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,"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-12-s3-s6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-12-s3-s6","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-12-S3-S6","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8299999833106995}],"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/W2024940313.pdf","grobid_xml":"https://content.openalex.org/works/W2024940313.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W116705248","https://openalex.org/W178298440","https://openalex.org/W1484050045","https://openalex.org/W1525742988","https://openalex.org/W1835371444","https://openalex.org/W1933390880","https://openalex.org/W1991154713","https://openalex.org/W2061167720","https://openalex.org/W2091825929","https://openalex.org/W2114420708","https://openalex.org/W2127241285","https://openalex.org/W2134189109","https://openalex.org/W2161132397","https://openalex.org/W2163303745"],"related_works":["https://openalex.org/W4255837520","https://openalex.org/W2387011115","https://openalex.org/W2626808643","https://openalex.org/W2319969327","https://openalex.org/W4234808182","https://openalex.org/W2004064826","https://openalex.org/W42295635","https://openalex.org/W4255628145","https://openalex.org/W3103727510","https://openalex.org/W2382043075"],"abstract_inverted_index":{"BACKGROUND:":[0],"The":[1,136],"rapid":[2],"growth":[3],"of":[4,25,104,147,176,204,212,236,241],"biomedical":[5],"literature":[6],"requires":[7],"accurate":[8],"text":[9,12,100],"analysis":[10],"and":[11,17,52,183,197,209,226],"processing":[13],"tools.":[14,27],"Detecting":[15],"abbreviations":[16,131],"identifying":[18],"their":[19],"definitions":[20],"is":[21,139,239],"an":[22,202,210],"important":[23],"component":[24],"such":[26],"Most":[28],"existing":[29,195],"approaches":[30],"for":[31,95],"the":[32,49,76,150,158,174,180,194,221],"abbreviation":[33,69,96,159],"definition":[34,58,97],"identification":[35,98],"task":[36],"employ":[37],"rule-based":[38,44],"methods.":[39],"While":[40],"achieving":[41],"high":[42],"precision,":[43],"methods":[45],"are":[46,114,125,154,218],"limited":[47],"to":[48,54,75,141,156,193,220],"rules":[50],"defined":[51],"fail":[53],"capture":[55],"many":[56],"uncommon":[57],"patterns.":[59],"Supervised":[60],"learning":[61,93],"techniques,":[62],"which":[63,101,217,238],"offer":[64],"more":[65],"flexibility":[66],"in":[67,99,120,234],"detecting":[68],"definitions,":[70],"have":[71],"also":[72],"been":[73],"applied":[74],"problem.":[77],"However,":[78],"they":[79],"require":[80,166],"manually":[81,167],"labeled":[82,109,168],"training":[83,112,123,169],"data.":[84,110,170],"METHODS:":[85],"In":[86],"this":[87],"work,":[88],"we":[89,106,230],"develop":[90],"a":[91],"machine":[92,137],"algorithm":[94,178],"makes":[102],"use":[103],"what":[105],"term":[107],"naturally":[108,115],"Positive":[111],"examples":[113,124],"occurring":[116],"potential":[117,130,134],"abbreviation-definition":[118],"pairs":[119],"text.":[121],"Negative":[122],"generated":[126],"by":[127,224],"randomly":[128],"mixing":[129],"with":[132],"unrelated":[133],"definitions.":[135],"learner":[138],"trained":[140],"distinguish":[142],"between":[143],"these":[144,232],"two":[145],"sets":[146],"examples.":[148],"Then,":[149],"learned":[151],"feature":[152],"weights":[153],"used":[155],"identify":[157],"full":[160],"form.":[161],"This":[162],"approach":[163],"does":[164],"not":[165],"RESULTS:":[171],"We":[172,200],"evaluate":[173],"performance":[175],"our":[177,242],"on":[179,206,214],"Ab3P,":[181],"BIOADI":[182,198,215,227],"Medstract":[184],"corpora.":[185],"Our":[186],"system":[187],"demonstrated":[188],"results":[189,222],"that":[190],"compare":[191],"favourably":[192],"Ab3P":[196,207,225],"systems.":[199,228],"achieve":[201],"F-measure":[203,211],"91.36%":[205],"corpus,":[208],"87.13%":[213],"corpus":[216],"superior":[219],"reported":[223],"Moreover,":[229],"outperform":[231],"systems":[233],"terms":[235],"recall,":[237],"one":[240],"goals.":[243]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}