{"id":"https://openalex.org/W4406461597","doi":"https://doi.org/10.1109/slt61566.2024.10832347","title":"Conditional Label Smoothing For LLM-Based Data Augmentation in Medical Text Classification","display_name":"Conditional Label Smoothing For LLM-Based Data Augmentation in Medical Text Classification","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461597","doi":"https://doi.org/10.1109/slt61566.2024.10832347"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832347","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030293327","display_name":"Luca Becker","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Luca Becker","raw_affiliation_strings":["Institute of Communication Acoustics, Ruhr-Universitüt Bochum,Bochum,Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Communication Acoustics, Ruhr-Universitüt Bochum,Bochum,Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062602281","display_name":"Philip Pracht","orcid":null},"institutions":[{"id":"https://openalex.org/I4210138213","display_name":"Bochumer Institut f\u00fcr Technologie (Germany)","ror":"https://ror.org/0432w2a74","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210138213"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Philip Pracht","raw_affiliation_strings":["Bochum Institute of Technology,Bochum,Germany"],"affiliations":[{"raw_affiliation_string":"Bochum Institute of Technology,Bochum,Germany","institution_ids":["https://openalex.org/I4210138213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115905169","display_name":"Peter Sertdal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter Sertdal","raw_affiliation_strings":["Institute of Communication Acoustics, Ruhr-Universitüt Bochum,Bochum,Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Communication Acoustics, Ruhr-Universitüt Bochum,Bochum,Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115905170","display_name":"Jil Uboreck","orcid":null},"institutions":[{"id":"https://openalex.org/I4210138213","display_name":"Bochumer Institut f\u00fcr Technologie (Germany)","ror":"https://ror.org/0432w2a74","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210138213"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jil Uboreck","raw_affiliation_strings":["Bochum Institute of Technology,Bochum,Germany"],"affiliations":[{"raw_affiliation_string":"Bochum Institute of Technology,Bochum,Germany","institution_ids":["https://openalex.org/I4210138213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074127200","display_name":"Alexander Bendel","orcid":null},"institutions":[{"id":"https://openalex.org/I62318514","display_name":"University of Duisburg-Essen","ror":"https://ror.org/04mz5ra38","country_code":"DE","type":"education","lineage":["https://openalex.org/I62318514"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander Bendel","raw_affiliation_strings":["Institute for Work and Qualification, University of Duisburg-Essen,Essen,Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Work and Qualification, University of Duisburg-Essen,Essen,Germany","institution_ids":["https://openalex.org/I62318514"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064880163","display_name":"Rainer Martin","orcid":"https://orcid.org/0000-0002-9587-4215"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rainer Martin","raw_affiliation_strings":["Institute of Communication Acoustics, Ruhr-Universitüt Bochum,Bochum,Germany"],"affiliations":[{"raw_affiliation_string":"Institute of Communication Acoustics, Ruhr-Universitüt Bochum,Bochum,Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5030293327"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23832463,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"833","last_page":"840"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9976000189781189,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9976000189781189,"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":0.9944000244140625,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9793000221252441,"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/smoothing","display_name":"Smoothing","score":0.7887810468673706},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6932872533798218},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4668484330177307},{"id":"https://openalex.org/keywords/multi-label-classification","display_name":"Multi-label classification","score":0.44817909598350525},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.388619601726532},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3821678161621094},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3630525767803192},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3424203395843506},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.09376001358032227}],"concepts":[{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.7887810468673706},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6932872533798218},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4668484330177307},{"id":"https://openalex.org/C2776482837","wikidata":"https://www.wikidata.org/wiki/Q3553958","display_name":"Multi-label classification","level":2,"score":0.44817909598350525},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.388619601726532},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3821678161621094},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3630525767803192},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3424203395843506},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.09376001358032227}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832347","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4699999988079071}],"awards":[],"funders":[{"id":"https://openalex.org/F4320311649","display_name":"Ministry of Education","ror":"https://ror.org/036nq5137"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2095705004","https://openalex.org/W2187089797","https://openalex.org/W2746791326","https://openalex.org/W2752349109","https://openalex.org/W2884561390","https://openalex.org/W2905266130","https://openalex.org/W2911489562","https://openalex.org/W2963341956","https://openalex.org/W2963545917","https://openalex.org/W2971296908","https://openalex.org/W2998184481","https://openalex.org/W3034999214","https://openalex.org/W3173941845","https://openalex.org/W4285310604","https://openalex.org/W4292779060","https://openalex.org/W4311000453","https://openalex.org/W4364378939","https://openalex.org/W4379468930","https://openalex.org/W4381930847","https://openalex.org/W4389520065","https://openalex.org/W4389520455","https://openalex.org/W4389520670","https://openalex.org/W4391126287","https://openalex.org/W6674330103","https://openalex.org/W6778883912","https://openalex.org/W6847363464","https://openalex.org/W6852584927"],"related_works":["https://openalex.org/W1978572805","https://openalex.org/W2383807498","https://openalex.org/W1997992934","https://openalex.org/W1987225439","https://openalex.org/W4238188170","https://openalex.org/W2125114371","https://openalex.org/W2019977573","https://openalex.org/W2149980199","https://openalex.org/W3125766170","https://openalex.org/W4281776617"],"abstract_inverted_index":{"In":[0,58],"this":[1],"paper,":[2],"we":[3,32,68,83,114],"propose":[4],"and":[5,28,37,126,140],"evaluate":[6,105],"a":[7,19,29,47,85,141],"data":[8,27,44,112,124],"augmentation":[9,125],"technique":[10],"for":[11,52,62],"improving":[12],"the":[13,53,65,75,93,117],"classification":[14,54,94],"of":[15,25,55,120],"text":[16,35,111],"data.":[17],"Using":[18],"large":[20],"language":[21],"model":[22],"(LLM),":[23],"samples":[24,36],"real-world":[26,43],"tailored":[30],"prompt,":[31],"generate":[33],"additional":[34],"use":[38],"these":[39],"in":[40,64,123],"combination":[41],"with":[42],"to":[45,60,73,91,130,136],"train":[46],"deep":[48],"neural":[49],"network":[50],"(DNN)":[51],"medical":[56,110],"sentences.":[57,81],"order":[59],"compensate":[61],"variations":[63],"augmented":[66],"data,":[67],"apply":[69],"label":[70,87,98],"smoothing":[71,88],"(LS)":[72],"render":[74],"DNN":[76],"more":[77],"robust":[78],"against":[79],"mislabeled":[80],"Moreover,":[82],"introduce":[84],"conditional":[86],"(CLS)":[89],"approach":[90],"exploit":[92],"statistics.":[95],"CLS":[96,129,146],"re-parameterizes":[97],"noise,":[99],"effectively":[100],"reducing":[101],"inter-class":[102],"confusion.":[103],"We":[104],"our":[106],"system":[107],"on":[108],"privacy-sensitive":[109],"where":[113],"first":[115],"show":[116],"general":[118],"benefits":[119],"using":[121],"LS":[122,133],"secondly":[127],"compare":[128],"LS.":[131,150],"While":[132],"already":[134],"leads":[135],"an":[137],"improved":[138],"F1-score":[139],"better":[142],"false":[143],"negative":[144],"rate,":[145],"slightly":[147],"outperforms":[148],"ordinary":[149]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}