{"id":"https://openalex.org/W1976330285","doi":"https://doi.org/10.1186/1472-6947-15-s1-s2","title":"Parsing clinical text: how good are the state-of-the-art parsers?","display_name":"Parsing clinical text: how good are the state-of-the-art parsers?","publication_year":2015,"publication_date":"2015-05-20","ids":{"openalex":"https://openalex.org/W1976330285","doi":"https://doi.org/10.1186/1472-6947-15-s1-s2","mag":"1976330285","pmid":"https://pubmed.ncbi.nlm.nih.gov/26045009"},"language":"en","primary_location":{"id":"doi:10.1186/1472-6947-15-s1-s2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1472-6947-15-s1-s2","pdf_url":"https://bmcmedinformdecismak.biomedcentral.com/counter/pdf/10.1186/1472-6947-15-S1-S2","source":{"id":"https://openalex.org/S107516304","display_name":"BMC Medical Informatics and Decision Making","issn_l":"1472-6947","issn":["1472-6947"],"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 Medical Informatics and Decision Making","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcmedinformdecismak.biomedcentral.com/counter/pdf/10.1186/1472-6947-15-S1-S2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055848133","display_name":"Min Jiang","orcid":"https://orcid.org/0000-0002-1407-0961"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Min Jiang","raw_affiliation_strings":["The University of Texas School of Biomedical Informatics at Houston, Houston, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas School of Biomedical Informatics at Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101682935","display_name":"Yang Huang","orcid":"https://orcid.org/0000-0002-9551-4447"},"institutions":[{"id":"https://openalex.org/I4210091210","display_name":"Kaiser Permanente San Diego Medical Center","ror":"https://ror.org/00fg98b82","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1343052199","https://openalex.org/I4210091210"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Huang","raw_affiliation_strings":["Kaiser Permanente, San Diego, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kaiser Permanente, San Diego, CA, USA","institution_ids":["https://openalex.org/I4210091210"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043910718","display_name":"Jungwei Fan","orcid":"https://orcid.org/0000-0001-6349-3752"},"institutions":[{"id":"https://openalex.org/I4210091210","display_name":"Kaiser Permanente San Diego Medical Center","ror":"https://ror.org/00fg98b82","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1343052199","https://openalex.org/I4210091210"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jung-wei Fan","raw_affiliation_strings":["Kaiser Permanente, San Diego, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kaiser Permanente, San Diego, CA, USA","institution_ids":["https://openalex.org/I4210091210"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014238603","display_name":"Buzhou Tang","orcid":"https://orcid.org/0000-0003-0271-8246"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Buzhou Tang","raw_affiliation_strings":["Shenzhen Graduate School of Harbin institute of Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Graduate School of Harbin institute of Technology, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070908224","display_name":"Joshua C. Denny","orcid":"https://orcid.org/0000-0002-3049-7332"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Josh Denny","raw_affiliation_strings":["Department of Biomedical Informatics, Vanderbilt University, School of Medicine, Nashville, TN, USA","Department of Medicine, Vanderbilt University, School of Medicine Nashville, TN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Vanderbilt University, School of Medicine, Nashville, TN, USA","institution_ids":["https://openalex.org/I200719446"]},{"raw_affiliation_string":"Department of Medicine, Vanderbilt University, School of Medicine Nashville, TN, USA","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084072550","display_name":"Hua Xu","orcid":"https://orcid.org/0000-0002-5274-4672"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hua Xu","raw_affiliation_strings":["The University of Texas School of Biomedical Informatics at Houston, Houston, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas School of Biomedical Informatics at Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I44461941"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5055848133"],"corresponding_institution_ids":["https://openalex.org/I44461941"],"apc_list":{"value":1570,"currency":"GBP","value_usd":1925},"apc_paid":{"value":1570,"currency":"GBP","value_usd":1925},"fwci":3.116,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.92659853,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"15","issue":"S1","first_page":"S2","last_page":"S2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.6061999797821045,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.6061999797821045,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.10130000114440918,"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/T13629","display_name":"Text Readability and Simplification","score":0.05649999901652336,"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/treebank","display_name":"Treebank","score":0.9684864282608032},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8141591548919678},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.798589289188385},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.760765552520752},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7582598924636841},{"id":"https://openalex.org/keywords/bracketing","display_name":"Bracketing (phenomenology)","score":0.7408807277679443},{"id":"https://openalex.org/keywords/parser-combinator","display_name":"Parser combinator","score":0.5688230991363525},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4402448236942291}],"concepts":[{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.9684864282608032},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8141591548919678},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.798589289188385},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.760765552520752},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7582598924636841},{"id":"https://openalex.org/C102944935","wikidata":"https://www.wikidata.org/wiki/Q4953701","display_name":"Bracketing (phenomenology)","level":2,"score":0.7408807277679443},{"id":"https://openalex.org/C118364021","wikidata":"https://www.wikidata.org/wiki/Q7139956","display_name":"Parser combinator","level":3,"score":0.5688230991363525},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4402448236942291},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008037","descriptor_name":"Linguistics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D008037","descriptor_name":"Linguistics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D008037","descriptor_name":"Linguistics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D008490","descriptor_name":"Medical Informatics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D008490","descriptor_name":"Medical Informatics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D008490","descriptor_name":"Medical Informatics","qualifier_ui":"Q000379","qualifier_name":"methods","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}],"locations_count":3,"locations":[{"id":"doi:10.1186/1472-6947-15-s1-s2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1472-6947-15-s1-s2","pdf_url":"https://bmcmedinformdecismak.biomedcentral.com/counter/pdf/10.1186/1472-6947-15-S1-S2","source":{"id":"https://openalex.org/S107516304","display_name":"BMC Medical Informatics and Decision Making","issn_l":"1472-6947","issn":["1472-6947"],"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 Medical Informatics and Decision Making","raw_type":"journal-article"},{"id":"pmid:26045009","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/26045009","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 medical informatics and decision making","raw_type":null},{"id":"pmh:oai:europepmc.org:3442863","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4460747","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":"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"}],"best_oa_location":{"id":"doi:10.1186/1472-6947-15-s1-s2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1472-6947-15-s1-s2","pdf_url":"https://bmcmedinformdecismak.biomedcentral.com/counter/pdf/10.1186/1472-6947-15-S1-S2","source":{"id":"https://openalex.org/S107516304","display_name":"BMC Medical Informatics and Decision Making","issn_l":"1472-6947","issn":["1472-6947"],"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 Medical Informatics and Decision Making","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8100000023841858,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G5278278750","display_name":null,"funder_award_id":"1R01GM102282","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"},{"id":"https://openalex.org/G5459461225","display_name":null,"funder_award_id":"1R01GM102282","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G8984988633","display_name":null,"funder_award_id":"2R01LM010681-05","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"}],"funders":[{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1976330285.pdf","grobid_xml":"https://content.openalex.org/works/W1976330285.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W64002976","https://openalex.org/W101452087","https://openalex.org/W108437174","https://openalex.org/W122290181","https://openalex.org/W152958635","https://openalex.org/W202643521","https://openalex.org/W1425787433","https://openalex.org/W1504212872","https://openalex.org/W1511777660","https://openalex.org/W1550258693","https://openalex.org/W1602357614","https://openalex.org/W1632114991","https://openalex.org/W1648311451","https://openalex.org/W1818857488","https://openalex.org/W2032235985","https://openalex.org/W2093157872","https://openalex.org/W2097606805","https://openalex.org/W2111519552","https://openalex.org/W2114388055","https://openalex.org/W2125712079","https://openalex.org/W2129817520","https://openalex.org/W2134498732","https://openalex.org/W2138382875","https://openalex.org/W2146089916","https://openalex.org/W2148349752","https://openalex.org/W2153439141","https://openalex.org/W2156518033","https://openalex.org/W2159636537","https://openalex.org/W2163568299","https://openalex.org/W2288093748","https://openalex.org/W2305592425","https://openalex.org/W2615753704","https://openalex.org/W2911934800","https://openalex.org/W2912457155","https://openalex.org/W2913539360","https://openalex.org/W2915027006","https://openalex.org/W2950064328"],"related_works":["https://openalex.org/W2072743731","https://openalex.org/W2019068568","https://openalex.org/W44286443","https://openalex.org/W2250416224","https://openalex.org/W1585034923","https://openalex.org/W1818857488","https://openalex.org/W3011924861","https://openalex.org/W2789919619","https://openalex.org/W2044122727","https://openalex.org/W1976330285"],"abstract_inverted_index":{"BACKGROUND:":[0],"Parsing,":[1],"which":[2,122],"generates":[3],"a":[4,8,14,112],"syntactic":[5],"structure":[6],"of":[7,17,54,69,147,212,244,269,281,294],"sentence":[9],"(a":[10],"parse":[11],"tree),":[12],"is":[13,123,309],"critical":[15,310],"component":[16],"natural":[18],"language":[19],"processing":[20],"(NLP)":[21],"research":[22],"in":[23,31,57,101,204,209],"any":[24],"domain":[25,325],"including":[26],"medicine.":[27],"Although":[28],"parsers":[29,151,164,183,200,226],"developed":[30,124],"the":[32,38,58,67,73,76,80,102,119,145,148,153,163,166,174,182,186,190,198,210,222,231,235,240,252,260,270,273,277,287,291,297],"general":[33,216,313],"English":[34,217,314],"domain,":[35],"such":[36],"as":[37],"Stanford":[39,74,236,288],"parser,":[40,75,78,82],"have":[41],"been":[42],"applied":[43],"to":[44,111,215],"clinical":[45,130,154,167,187,205,223,262,307,318,322,333],"text,":[46,319],"there":[47],"are":[48],"no":[49],"formal":[50],"evaluations":[51],"and":[52,79,107,117,129,169,249,264,286,320,323],"comparisons":[53],"their":[55,157,171],"performance":[56,68,146,172,203,233,316,330],"medical":[59],"domain.":[60],"METHODS:":[61],"In":[62],"this":[63],"study,":[64],"we":[65,143,161,180],"investigated":[66],"three":[70,137,149,271],"state-of-the-art":[71,150],"parsers:":[72],"Bikel":[77],"Charniak":[81,274],"using":[83,165,173,255,306],"following":[84],"two":[85],"datasets:":[86],"(1)":[87],"A":[88],"Treebank":[89,114,266],"containing":[90,132],"1,100":[91],"sentences":[92],"that":[93,197,238,304],"were":[94],"randomly":[95],"selected":[96],"from":[97,234],"progress":[98,247,284],"notes":[99,128,248,285],"used":[100],"2010":[103],"i2b2":[104],"NLP":[105],"challenge":[106],"manually":[108],"annotated":[109],"according":[110],"Penn":[113,191,265],"based":[115,125],"guideline;":[116],"(2)":[118],"MiPACQ":[120,253,298],"Treebank,":[121,224],"on":[126,139,152,221,246,251,283,296,317],"pathology":[127],"notes,":[131],"13,091":[133],"sentences.":[134],"We":[135],"conducted":[136],"experiments":[138],"both":[140],"datasets.":[141],"First,":[142],"measured":[144],"Treebanks":[155,168,188,263,308],"with":[156,189,230],"default":[158],"settings.":[159],"Then":[160],"re-trained":[162,181],"evaluated":[170],"10-fold":[175,256],"cross":[176,257],"validation":[177],"method.":[178],"Finally":[179],"by":[184],"combining":[185,321],"Treebank.":[192],"RESULTS:":[193],"Our":[194,301],"results":[195],"showed":[196],"original":[199],"achieved":[201,227,276],"lower":[202],"text":[206],"(Bracketing":[207],"F-measure":[208,243,280,293],"range":[211],"66.6%-70.3%)":[213],"compared":[214],"text.":[218,334],"After":[219],"retraining":[220],"all":[225],"better":[228],"performance,":[229],"best":[232],"parser":[237,275,289],"reached":[239,290],"highest":[241,278,292],"Bracketing":[242,279],"73.68%":[245],"83.72%":[250],"corpus":[254],"validation.":[258],"When":[259],"combined":[261],"was":[267],"used,":[268],"parsers,":[272],"73.53%":[282],"84.15%":[295],"corpus.":[299],"CONCLUSIONS:":[300],"study":[302],"demonstrates":[303],"re-training":[305],"for":[311,331],"improving":[312],"parsers'":[315],"open":[324],"corpora":[326],"might":[327],"achieve":[328],"optimal":[329],"parsing":[332]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2016,"cited_by_count":3}],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-10T00:00:00"}