{"id":"https://openalex.org/W2251868561","doi":"https://doi.org/10.3115/v1/w14-4913","title":"Annotating a Large Representative Corpus of Clinical Notes for Parts of Speech","display_name":"Annotating a Large Representative Corpus of Clinical Notes for Parts of Speech","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2251868561","doi":"https://doi.org/10.3115/v1/w14-4913","mag":"2251868561"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w14-4913","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-4913","pdf_url":"https://aclanthology.org/W14-4913.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of LAW VIII - The 8th Linguistic Annotation Workshop","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/W14-4913.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031772528","display_name":"Narayan Choudhary","orcid":"https://orcid.org/0000-0002-2116-5205"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Narayan Choudhary","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068786874","display_name":"Parth Pathak","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Parth Pathak","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101230917","display_name":"Pinal Patel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pinal Patel","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5052731640","display_name":"Vishal Panchal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vishal Panchal","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5031772528"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.818,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.82116367,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"87","last_page":"92"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9970999956130981,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9947999715805054,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/treebank","display_name":"Treebank","score":0.9477419853210449},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8462755680084229},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7591208219528198},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6695998907089233},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6473276615142822},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.5228205919265747},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4685559868812561},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3554217517375946}],"concepts":[{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.9477419853210449},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8462755680084229},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7591208219528198},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6695998907089233},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6473276615142822},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.5228205919265747},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4685559868812561},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3554217517375946},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3115/v1/w14-4913","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-4913","pdf_url":"https://aclanthology.org/W14-4913.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of LAW VIII - The 8th Linguistic Annotation Workshop","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.3115/v1/w14-4913","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-4913","pdf_url":"https://aclanthology.org/W14-4913.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of LAW VIII - The 8th Linguistic Annotation Workshop","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2251868561.pdf","grobid_xml":"https://content.openalex.org/works/W2251868561.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1507020546","https://openalex.org/W1632114991","https://openalex.org/W1666538313","https://openalex.org/W1967866551","https://openalex.org/W1996430422","https://openalex.org/W2080637049","https://openalex.org/W2097606805","https://openalex.org/W2120354757","https://openalex.org/W2125712079","https://openalex.org/W2134498732","https://openalex.org/W2135843243","https://openalex.org/W2140398982","https://openalex.org/W2151532143","https://openalex.org/W2170986599","https://openalex.org/W2394935510","https://openalex.org/W2950121111","https://openalex.org/W3146885639"],"related_works":["https://openalex.org/W2404671839","https://openalex.org/W2048063563","https://openalex.org/W3030001591","https://openalex.org/W2589201127","https://openalex.org/W2033043215","https://openalex.org/W2251524673","https://openalex.org/W2182012814","https://openalex.org/W139168100","https://openalex.org/W1993844325","https://openalex.org/W2126647499"],"abstract_inverted_index":{"We":[0,153],"report":[1,155],"of":[2,5,11,20,23,37,55,69,81,100,112,123,143,158,173],"the":[3,34,82,92,128,135,141,144,150,156,159,164],"procedures":[4],"developing":[6],"a":[7,50,98,121,170],"large":[8,52],"representative":[9],"corpus":[10,22,45,54,105,126],"50,000":[12],"sentences":[13,41,168],"taken":[14,74],"from":[15,49,65,75],"clinical":[16,24,38,129,151],"notes.":[17,39],"Previous":[18],"reports":[19],"annotated":[21,125,167],"notes":[25],"have":[26,46],"been":[27,47],"small":[28],"and":[29,138],"they":[30],"do":[31],"not":[32],"represent":[33],"whole":[35],"domain":[36,130],"The":[40,116],"included":[42],"in":[43,127,149],"this":[44,104],"selected":[48],"very":[51],"raw":[53],"ten":[56,60],"thousand":[57,61],"documents.":[58],"These":[59],"documents":[62,73,83],"are":[63],"sampled":[64],"an":[66,108],"internal":[67],"repository":[68],"more":[70,113],"than":[71,114],"700,000":[72],"multiple":[76],"health":[77],"care":[78],"providers.":[79],"Each":[80],"is":[84,118,132],"de-identified":[85],"to":[86,119,134],"remove":[87],"any":[88],"PHI":[89],"data.":[90],"Using":[91],"Penn":[93,136],"Treebank":[94,137],"tagging":[95],"guidelines":[96],"with":[97,107],"bit":[99],"modifications,":[101],"we":[102],"annotate":[103],"manually":[106],"average":[109],"inter-annotator":[110],"agreement":[111],"98%.":[115],"goal":[117],"create":[120],"parts":[122],"speech":[124],"that":[131],"comparable":[133],"also":[139,154],"represents":[140],"totality":[142],"contemporary":[145],"text":[146],"as":[147],"used":[148],"domain.":[152],"output":[157],"TnT":[160],"tagger":[161],"trained":[162],"on":[163],"initial":[165],"21,000":[166],"reaching":[169],"preliminary":[171],"accuracy":[172],"above":[174],"96%.]":[175]},"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}