{"id":"https://openalex.org/W4387848931","doi":"https://doi.org/10.1145/3583780.3615146","title":"Retrieval-Based Unsupervised Noisy Label Detection on Text Data","display_name":"Retrieval-Based Unsupervised Noisy Label Detection on Text Data","publication_year":2023,"publication_date":"2023-10-21","ids":{"openalex":"https://openalex.org/W4387848931","doi":"https://doi.org/10.1145/3583780.3615146"},"language":"en","primary_location":{"id":"doi:10.1145/3583780.3615146","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3583780.3615146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","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/A5042572820","display_name":"Peiyang Liu","orcid":"https://orcid.org/0000-0003-3658-9147"},"institutions":[{"id":"https://openalex.org/I4210106409","display_name":"China Institute of Finance and Capital Markets","ror":"https://ror.org/01mp98161","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210106409"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peiyang Liu","raw_affiliation_strings":["PX Securities, Shen Zhen, China"],"raw_orcid":"https://orcid.org/0000-0003-3658-9147","affiliations":[{"raw_affiliation_string":"PX Securities, Shen Zhen, China","institution_ids":["https://openalex.org/I4210106409"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103047322","display_name":"J. C. S. Yang","orcid":"https://orcid.org/0009-0006-5367-094X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinyu Yang","raw_affiliation_strings":["Shanxi Institute of Energy, JIn Zhong, China"],"raw_orcid":"https://orcid.org/0009-0006-5367-094X","affiliations":[{"raw_affiliation_string":"Shanxi Institute of Energy, JIn Zhong, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103050645","display_name":"Lin Wang","orcid":"https://orcid.org/0009-0008-4691-1287"},"institutions":[{"id":"https://openalex.org/I4210106409","display_name":"China Institute of Finance and Capital Markets","ror":"https://ror.org/01mp98161","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210106409"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Wang","raw_affiliation_strings":["PX Securities, Shen Zhen, China"],"raw_orcid":"https://orcid.org/0009-0008-4691-1287","affiliations":[{"raw_affiliation_string":"PX Securities, Shen Zhen, China","institution_ids":["https://openalex.org/I4210106409"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015032241","display_name":"Sen Wang","orcid":"https://orcid.org/0009-0003-4527-3416"},"institutions":[{"id":"https://openalex.org/I4210106409","display_name":"China Institute of Finance and Capital Markets","ror":"https://ror.org/01mp98161","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210106409"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sen Wang","raw_affiliation_strings":["PX Securities, Shen Zhen, China"],"raw_orcid":"https://orcid.org/0009-0003-4527-3416","affiliations":[{"raw_affiliation_string":"PX Securities, Shen Zhen, China","institution_ids":["https://openalex.org/I4210106409"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038363974","display_name":"Yikuang Hao","orcid":"https://orcid.org/0009-0006-9494-4257"},"institutions":[{"id":"https://openalex.org/I4210106409","display_name":"China Institute of Finance and Capital Markets","ror":"https://ror.org/01mp98161","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210106409"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunlai Hao","raw_affiliation_strings":["PX Securities, Shen Zhen, China"],"raw_orcid":"https://orcid.org/0009-0006-9494-4257","affiliations":[{"raw_affiliation_string":"PX Securities, Shen Zhen, China","institution_ids":["https://openalex.org/I4210106409"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015861461","display_name":"Hongzhou Bai","orcid":"https://orcid.org/0009-0009-5722-6784"},"institutions":[{"id":"https://openalex.org/I4210106409","display_name":"China Institute of Finance and Capital Markets","ror":"https://ror.org/01mp98161","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210106409"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huihui Bai","raw_affiliation_strings":["PX Securities, Shen Zhen, China"],"raw_orcid":"https://orcid.org/0009-0009-5722-6784","affiliations":[{"raw_affiliation_string":"PX Securities, Shen Zhen, China","institution_ids":["https://openalex.org/I4210106409"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4099","last_page":"4104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9975000023841858,"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":0.9975000023841858,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9972000122070312,"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":0.9666000008583069,"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/overfitting","display_name":"Overfitting","score":0.8979815244674683},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8381217122077942},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6374813914299011},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.5771944522857666},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5687384009361267},{"id":"https://openalex.org/keywords/data-cleansing","display_name":"Data cleansing","score":0.5646206140518188},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5421044230461121},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5323788523674011},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4732837378978729},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.47155284881591797},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.43821319937705994},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41209617257118225},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3758586049079895},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.28806912899017334}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8979815244674683},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8381217122077942},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6374813914299011},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.5771944522857666},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5687384009361267},{"id":"https://openalex.org/C42199009","wikidata":"https://www.wikidata.org/wiki/Q1172378","display_name":"Data cleansing","level":4,"score":0.5646206140518188},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5421044230461121},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5323788523674011},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4732837378978729},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47155284881591797},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.43821319937705994},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41209617257118225},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3758586049079895},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.28806912899017334},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"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/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3583780.3615146","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3583780.3615146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.5899999737739563,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W1552847225","https://openalex.org/W1997452128","https://openalex.org/W2113459411","https://openalex.org/W2560674852","https://openalex.org/W2747329762","https://openalex.org/W2912924812","https://openalex.org/W2921491036","https://openalex.org/W2963748441","https://openalex.org/W2988966271","https://openalex.org/W3034185248","https://openalex.org/W3104382126","https://openalex.org/W3156669901","https://openalex.org/W3168051837","https://openalex.org/W3210618910","https://openalex.org/W3213768855","https://openalex.org/W4221161368","https://openalex.org/W4312305885","https://openalex.org/W4312682661","https://openalex.org/W4313135270"],"related_works":["https://openalex.org/W3172936821","https://openalex.org/W2978625989","https://openalex.org/W2951459130","https://openalex.org/W2153316431","https://openalex.org/W3042497982","https://openalex.org/W167284613","https://openalex.org/W2107233456","https://openalex.org/W1577350436","https://openalex.org/W4387848931","https://openalex.org/W2352224576"],"abstract_inverted_index":{"The":[0,55],"success":[1],"of":[2,14,58,111,117],"deep":[3],"neural":[4],"networks":[5],"hinges":[6],"on":[7,68],"both":[8],"high-quality":[9],"annotations":[10],"and":[11,24,30,35,95],"copious":[12],"amounts":[13],"data;":[15],"however,":[16],"in":[17,91,98,122],"practice,":[18],"a":[19,96,104],"compromise":[20],"between":[21],"dataset":[22],"size":[23],"quality":[25],"frequently":[26],"arises.":[27],"Data":[28],"collection":[29],"cleansing":[31],"are":[32],"often":[33,84],"resource-intensive":[34],"time-consuming,":[36],"leading":[37],"to":[38,73],"real-world":[39],"datasets":[40],"containing":[41],"label":[42],"noise":[43],"that":[44],"can":[45],"introduce":[46],"incorrect":[47],"correlation":[48],"patterns,":[49],"adversely":[50],"affecting":[51],"model":[52],"generalization":[53],"capabilities.":[54],"efficient":[56],"identification":[57],"corrupted":[59,93],"patterns":[60,94],"is":[61],"indispensable,":[62],"with":[63],"prevalent":[64],"methods":[65,121],"predominantly":[66],"concentrating":[67],"devising":[69],"robust":[70],"training":[71,87],"techniques":[72],"preclude":[74],"models":[75],"from":[76],"internalizing":[77],"these":[78,81],"patterns.":[79],"Nevertheless,":[80],"supervised":[82],"approaches":[83],"necessitate":[85],"tailored":[86],"procedures,":[88],"potentially":[89],"resulting":[90],"overfitting":[92],"decline":[97],"detection":[99,110],"performance.":[100],"This":[101],"paper":[102],"presents":[103],"retrieval-based":[105],"unsupervised":[106],"solution":[107],"for":[108],"the":[109,115],"noisy":[112],"labels,":[113],"surpassing":[114],"performance":[116],"three":[118],"current":[119],"competitive":[120],"this":[123],"domain.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}