{"id":"https://openalex.org/W2101289003","doi":"https://doi.org/10.1197/jamia.m2392","title":"Heuristic Sample Selection to Minimize Reference Standard Training Set for a Part-Of-Speech Tagger","display_name":"Heuristic Sample Selection to Minimize Reference Standard Training Set for a Part-Of-Speech Tagger","publication_year":2007,"publication_date":"2007-06-28","ids":{"openalex":"https://openalex.org/W2101289003","doi":"https://doi.org/10.1197/jamia.m2392","mag":"2101289003","pmid":"https://pubmed.ncbi.nlm.nih.gov/17600099"},"language":"en","primary_location":{"id":"doi:10.1197/jamia.m2392","is_oa":true,"landing_page_url":"https://doi.org/10.1197/jamia.m2392","pdf_url":"https://academic.oup.com/jamia/article-pdf/14/5/641/2142976/14-5-641.pdf","source":{"id":"https://openalex.org/S129839026","display_name":"Journal of the American Medical Informatics Association","issn_l":"1067-5027","issn":["1067-5027","1527-974X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Medical Informatics Association","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/jamia/article-pdf/14/5/641/2142976/14-5-641.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016444578","display_name":"K. Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"K. Liu","raw_affiliation_strings":["Department of Biomedical Informatics, University of Pittsburgh School of Medicine, Pittsburgh, PA 15232, USA","Affiliations of the authors: Department of Biomedical Informatics (KL, WC, RSC), Department of Computer Science (RH), Department of Pathology (RSC), University of Pittsburgh School of Medicine, Pittsburgh, PA"],"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, University of Pittsburgh School of Medicine, Pittsburgh, PA 15232, USA","institution_ids":[]},{"raw_affiliation_string":"Affiliations of the authors: Department of Biomedical Informatics (KL, WC, RSC), Department of Computer Science (RH), Department of Pathology (RSC), University of Pittsburgh School of Medicine, Pittsburgh, PA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065170642","display_name":"Wendy W. Chapman","orcid":"https://orcid.org/0000-0001-8702-4483"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"W. Chapman","raw_affiliation_strings":["Affiliations of the authors: Department of Biomedical Informatics (KL, WC, RSC), Department of Computer Science (RH), Department of Pathology (RSC), University of Pittsburgh School of Medicine, Pittsburgh, PA"],"affiliations":[{"raw_affiliation_string":"Affiliations of the authors: Department of Biomedical Informatics (KL, WC, RSC), Department of Computer Science (RH), Department of Pathology (RSC), University of Pittsburgh School of Medicine, Pittsburgh, PA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070135550","display_name":"Rebecca Hwa","orcid":"https://orcid.org/0000-0003-1158-7014"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R. Hwa","raw_affiliation_strings":["Affiliations of the authors: Department of Biomedical Informatics (KL, WC, RSC), Department of Computer Science (RH), Department of Pathology (RSC), University of Pittsburgh School of Medicine, Pittsburgh, PA"],"affiliations":[{"raw_affiliation_string":"Affiliations of the authors: Department of Biomedical Informatics (KL, WC, RSC), Department of Computer Science (RH), Department of Pathology (RSC), University of Pittsburgh School of Medicine, Pittsburgh, PA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044313420","display_name":"Rebecca S. Crowley","orcid":null},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"R. S. Crowley","raw_affiliation_strings":["Affiliations of the authors: Department of Biomedical Informatics (KL, WC, RSC), Department of Computer Science (RH), Department of Pathology (RSC), University of Pittsburgh School of Medicine, Pittsburgh, PA"],"affiliations":[{"raw_affiliation_string":"Affiliations of the authors: Department of Biomedical Informatics (KL, WC, RSC), Department of Computer Science (RH), Department of Pathology (RSC), University of Pittsburgh School of Medicine, Pittsburgh, PA","institution_ids":["https://openalex.org/I170201317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5044313420"],"corresponding_institution_ids":["https://openalex.org/I170201317"],"apc_list":{"value":3967,"currency":"USD","value_usd":3967},"apc_paid":null,"fwci":3.8699,"has_fulltext":true,"cited_by_count":30,"citation_normalized_percentile":{"value":0.93616068,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"14","issue":"5","first_page":"641","last_page":"650"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9987999796867371,"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":0.9973999857902527,"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/computer-science","display_name":"Computer science","score":0.8382741212844849},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7027946710586548},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6404067873954773},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6279886364936829},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6196227669715881},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.575961172580719},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5704007148742676},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5493972301483154},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5416713953018188},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.48719853162765503},{"id":"https://openalex.org/keywords/part-of-speech","display_name":"Part of speech","score":0.4789848327636719},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.42831653356552124},{"id":"https://openalex.org/keywords/part-of-speech-tagging","display_name":"Part-of-speech tagging","score":0.41523969173431396},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39560407400131226},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3813727796077728},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07487839460372925}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8382741212844849},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7027946710586548},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6404067873954773},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6279886364936829},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6196227669715881},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.575961172580719},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5704007148742676},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5493972301483154},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5416713953018188},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.48719853162765503},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.4789848327636719},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.42831653356552124},{"id":"https://openalex.org/C2780684714","wikidata":"https://www.wikidata.org/wiki/Q1271424","display_name":"Part-of-speech tagging","level":3,"score":0.41523969173431396},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39560407400131226},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3813727796077728},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07487839460372925},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"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":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008037","descriptor_name":"Linguistics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008037","descriptor_name":"Linguistics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008037","descriptor_name":"Linguistics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008037","descriptor_name":"Linguistics","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":"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":"D009626","descriptor_name":"Terminology as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009626","descriptor_name":"Terminology as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009626","descriptor_name":"Terminology as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009626","descriptor_name":"Terminology as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010340","descriptor_name":"Pathology, Surgical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010340","descriptor_name":"Pathology, Surgical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010340","descriptor_name":"Pathology, Surgical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010340","descriptor_name":"Pathology, Surgical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1197/jamia.m2392","is_oa":true,"landing_page_url":"https://doi.org/10.1197/jamia.m2392","pdf_url":"https://academic.oup.com/jamia/article-pdf/14/5/641/2142976/14-5-641.pdf","source":{"id":"https://openalex.org/S129839026","display_name":"Journal of the American Medical Informatics Association","issn_l":"1067-5027","issn":["1067-5027","1527-974X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Medical Informatics Association","raw_type":"journal-article"},{"id":"pmid:17600099","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/17600099","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":"Journal of the American Medical Informatics Association : JAMIA","raw_type":null},{"id":"pmh:oai:d-scholarship.pitt.edu:13805","is_oa":false,"landing_page_url":"http://d-scholarship.pitt.edu/13805/1/licence.txt","pdf_url":null,"source":{"id":"https://openalex.org/S4306402375","display_name":"D-Scholarship@Pitt (University of Pittsburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I170201317","host_organization_name":"University of Pittsburgh","host_organization_lineage":["https://openalex.org/I170201317"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:1975798","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/1975798","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Am Med Inform Assoc","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1197/jamia.m2392","is_oa":true,"landing_page_url":"https://doi.org/10.1197/jamia.m2392","pdf_url":"https://academic.oup.com/jamia/article-pdf/14/5/641/2142976/14-5-641.pdf","source":{"id":"https://openalex.org/S129839026","display_name":"Journal of the American Medical Informatics Association","issn_l":"1067-5027","issn":["1067-5027","1527-974X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the American Medical Informatics Association","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2101289003.pdf","grobid_xml":"https://content.openalex.org/works/W2101289003.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W17967270","https://openalex.org/W192665053","https://openalex.org/W900993354","https://openalex.org/W1237926134","https://openalex.org/W1276094478","https://openalex.org/W1548184736","https://openalex.org/W1590983731","https://openalex.org/W1632114991","https://openalex.org/W1718065290","https://openalex.org/W1773803948","https://openalex.org/W1894968013","https://openalex.org/W1950048153","https://openalex.org/W1991746030","https://openalex.org/W1996430422","https://openalex.org/W2007367068","https://openalex.org/W2010588484","https://openalex.org/W2069912724","https://openalex.org/W2084956011","https://openalex.org/W2127241285","https://openalex.org/W2133362931","https://openalex.org/W2143078730","https://openalex.org/W2153439141","https://openalex.org/W2153804780","https://openalex.org/W2170381724","https://openalex.org/W2288055910","https://openalex.org/W4230722969"],"related_works":["https://openalex.org/W1999382833","https://openalex.org/W1965453504","https://openalex.org/W2396342956","https://openalex.org/W2169508526","https://openalex.org/W2486838646","https://openalex.org/W2626026432","https://openalex.org/W2251183413","https://openalex.org/W2949108231","https://openalex.org/W3128305375","https://openalex.org/W2006539681"],"abstract_inverted_index":{"Part-of-speech":[0],"tagging":[1],"represents":[2],"an":[3,188],"important":[4],"first":[5],"step":[6],"for":[7,63,161,218],"most":[8],"medical":[9,35,38,221],"natural":[10],"language":[11],"processing":[12],"(NLP)":[13],"systems.":[14,223],"The":[15],"majority":[16],"of":[17,45,80,169,194,220],"current":[18],"statistically-based":[19],"POS":[20,69],"taggers":[21],"are":[22,40],"trained":[23,114,131],"using":[24,94],"a":[25,53,65,73,85,143,199],"general":[26,116],"English":[27],"corpus.":[28],"Consequently,":[29],"these":[30],"systems":[31],"perform":[32],"poorly":[33],"on":[34,115,123,132],"text.":[36],"Annotated":[37],"corpora":[39],"difficult":[41],"to":[42,58,97,147,157,167,212],"develop":[43],"because":[44],"the":[46,92,104,109,119,124,128,138,148,152,170,192,195],"time":[47],"and":[48,84,102,126,154],"labor":[49],"required.":[50],"We":[51,71,90,203],"investigated":[52],"heuristic-based":[54],"sample":[55,162,184,207],"selection":[56,163,185,208],"method":[57],"minimize":[59],"annotated":[60,75],"corpus":[61,78],"size":[62,193],"retraining":[64],"Maximum":[66],"Entropy":[67],"(ME)":[68],"tagger.":[70],"developed":[72],"manually":[74],"domain":[76,86],"specific":[77,87],"(DSC)":[79],"surgical":[81],"pathology":[82],"reports":[83],"lexicon":[88],"(DL).":[89],"sampled":[91],"DSC":[93,144],"two":[95],"heuristics":[96],"produce":[98],"smaller":[99],"training":[100,172,196,219],"sets":[101],"compared":[103],"retrained":[105,122,141,150],"performance":[106,165],"against":[107],"(1)":[108],"original":[110],"ME":[111,120,139],"modeled":[112],"tagger":[113,121,130,140,149],"English,":[117],"(2)":[118],"DL,":[125,153],"(3)":[127],"MedPost":[129],"MEDLINE":[133],"abstracts.":[134],"RESULTS":[135],"showed":[136,182],"that":[137,183,205],"with":[142,151,175],"was":[145],"superior":[146,156],"also":[155],"MedPost.":[158],"Heuristic":[159],"methods":[160],"produced":[164],"equivalent":[166],"use":[168],"entire":[171],"set,":[173],"but":[174],"many":[176],"fewer":[177],"sentences.":[178],"Learning":[179],"curve":[180],"analysis":[181],"would":[186],"enable":[187],"84%":[189],"decrease":[190],"in":[191,201],"set":[197],"without":[198],"decrement":[200],"performance.":[202],"conclude":[204],"heuristic":[206],"can":[209],"be":[210],"used":[211],"markedly":[213],"reduce":[214],"human":[215],"annotation":[216],"requirements":[217],"NLP":[222]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":4}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}