{"id":"https://openalex.org/W3121951843","doi":"https://doi.org/10.1145/3459637.3482204","title":"Towards Robustness to Label Noise in Text Classification via Noise Modeling","display_name":"Towards Robustness to Label Noise in Text Classification via Noise Modeling","publication_year":2021,"publication_date":"2021-10-26","ids":{"openalex":"https://openalex.org/W3121951843","doi":"https://doi.org/10.1145/3459637.3482204","mag":"3121951843"},"language":"en","primary_location":{"id":"doi:10.1145/3459637.3482204","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2101.11214.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064222284","display_name":"Siddhant Garg","orcid":"https://orcid.org/0009-0004-0219-511X"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddhant Garg","raw_affiliation_strings":["Amazon Alexa AI, Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033403271","display_name":"Goutham Ramakrishnan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Goutham Ramakrishnan","raw_affiliation_strings":["Health at Scale Corporation, San Jose, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Health at Scale Corporation, San Jose, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041746505","display_name":"Varun Thumbe","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136525","display_name":"Technova Corporation (United States)","ror":"https://ror.org/03ksh5m61","country_code":"US","type":"company","lineage":["https://openalex.org/I4210136525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Varun Thumbe","raw_affiliation_strings":["KLA Corporation, Ann Arbor, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KLA Corporation, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I4210136525"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6997,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.75121546,"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":"3024","last_page":"3028"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","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/T12535","display_name":"Machine Learning and Data Classification","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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9962999820709229,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9939000010490417,"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/classifier","display_name":"Classifier (UML)","score":0.6923984885215759},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.689923882484436},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6334778070449829},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5329393148422241},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.48037442564964294},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4669063687324524},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.46345019340515137},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46277058124542236},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3622189164161682},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2879486680030823}],"concepts":[{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6923984885215759},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.689923882484436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6334778070449829},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5329393148422241},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.48037442564964294},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4669063687324524},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.46345019340515137},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46277058124542236},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3622189164161682},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2879486680030823},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3459637.3482204","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3459637.3482204","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},{"id":"mag:3121951843","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2101.11214.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2101.11214","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2101.11214","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"mag:3121951843","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2101.11214.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1832693441","https://openalex.org/W2043765769","https://openalex.org/W2054837316","https://openalex.org/W2064675550","https://openalex.org/W2070246124","https://openalex.org/W2098865355","https://openalex.org/W2157023969","https://openalex.org/W2167460663","https://openalex.org/W2250338295","https://openalex.org/W2250539671","https://openalex.org/W2518182934","https://openalex.org/W2765407302","https://openalex.org/W2769240247","https://openalex.org/W2798542376","https://openalex.org/W2890022946","https://openalex.org/W2917725866","https://openalex.org/W2928125049","https://openalex.org/W2941387380","https://openalex.org/W2950476261","https://openalex.org/W2951418570","https://openalex.org/W2962762541","https://openalex.org/W2963081269","https://openalex.org/W2963999980","https://openalex.org/W3137695714"],"related_works":["https://openalex.org/W3209934390","https://openalex.org/W3171635822","https://openalex.org/W1965759148","https://openalex.org/W3154948581","https://openalex.org/W2960998585","https://openalex.org/W2155881299","https://openalex.org/W2292982615","https://openalex.org/W3033172638","https://openalex.org/W2145580721","https://openalex.org/W3012026726","https://openalex.org/W2889604124","https://openalex.org/W2163921091","https://openalex.org/W2378170330","https://openalex.org/W2785967008","https://openalex.org/W2958623729","https://openalex.org/W3002173697","https://openalex.org/W2086581520","https://openalex.org/W2931104509","https://openalex.org/W2999438377","https://openalex.org/W2965521950"],"abstract_inverted_index":{"Large":[0],"datasets":[1],"in":[2],"NLP":[3],"tend":[4],"to":[5,11,30,48,154],"suffer":[6],"from":[7],"noisy":[8,57],"labels":[9],"due":[10],"erroneous":[12],"automatic":[13],"and":[14,28,81,104,134,141,151],"human":[15],"annotation":[16],"procedures.":[17],"We":[18,42],"study":[19],"the":[20,40,67,79,82,96,101,108,112,117,120,155],"problem":[21],"of":[22,52,95,107,119,137],"text":[23,131],"classification":[24,132,149],"with":[25,100,111],"label":[26,138],"noise,":[27],"aim":[29],"capture":[31],"this":[32],"noise":[33,37,83,97],"through":[34,85],"an":[35,71],"auxiliary":[36],"model":[38,64,84,98],"over":[39],"classifier.":[41],"first":[43],"assign":[44],"a":[45,54,60,86,123],"probability":[46,118],"score":[47],"each":[49],"training":[50,68],"sample":[51,121],"having":[53,90,122],"clean":[55,124],"or":[56],"label,":[58,103,114],"using":[59],"two-component":[61],"beta":[62],"mixture":[63],"fitted":[65],"on":[66,129],"losses":[69],"at":[70],"early":[72],"epoch.":[73],"Using":[74],"this,":[75],"we":[76],"jointly":[77],"train":[78],"classifier":[80,109],"novel":[87],"de-noising":[88],"loss":[89],"two":[91,130,135],"components:":[92],"(i)":[93],"cross-entropy":[94,106],"prediction":[99,110],"input":[102,113],"(ii)":[105],"weighted":[115],"by":[116],"label.":[125],"Our":[126],"empirical":[127],"evaluation":[128],"tasks":[133],"types":[136],"noise:":[139],"random":[140],"input-conditional,":[142],"shows":[143],"that":[144],"our":[145],"approach":[146],"can":[147],"improve":[148],"accuracy,":[150],"prevent":[152],"over-fitting":[153],"noise.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}