{"id":"https://openalex.org/W4385570089","doi":"https://doi.org/10.18653/v1/2023.findings-acl.239","title":"SANTA: Separate Strategies for Inaccurate and Incomplete Annotation Noise in Distantly-Supervised Named Entity Recognition","display_name":"SANTA: Separate Strategies for Inaccurate and Incomplete Annotation Noise in Distantly-Supervised Named Entity Recognition","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385570089","doi":"https://doi.org/10.18653/v1/2023.findings-acl.239"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.findings-acl.239","doi":"https://doi.org/10.18653/v1/2023.findings-acl.239","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-acl.239","pdf_url":"https://aclanthology.org/2023.findings-acl.239.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2023","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2023.findings-acl.239.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022397026","display_name":"Shuzheng Si","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuzheng Si","raw_affiliation_strings":["National Key Laboratory for Multimedia Information Processing, Peking University","School of Software and Microelectronics, Peking University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Multimedia Information Processing, Peking University","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Software and Microelectronics, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102312458","display_name":"Zefan Cai","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zefan Cai","raw_affiliation_strings":["National Key Laboratory for Multimedia Information Processing, Peking University","School of Software and Microelectronics, Peking University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Multimedia Information Processing, Peking University","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Software and Microelectronics, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109440703","display_name":"Shuang Zeng","orcid":"https://orcid.org/0009-0004-1936-3802","observed_orcids":["https://orcid.org/0009-0004-1936-3802","https://orcid.org/0009-0004-4477-8532"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuang Zeng","raw_affiliation_strings":["National Key Laboratory for Multimedia Information Processing, Peking University","School of Software and Microelectronics, Peking University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Multimedia Information Processing, Peking University","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Software and Microelectronics, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100696052","display_name":"Guoqiang Feng","orcid":"https://orcid.org/0009-0005-6617-2969","observed_orcids":["https://orcid.org/0009-0005-6617-2969"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoqiang Feng","raw_affiliation_strings":["National Key Laboratory for Multimedia Information Processing, Peking University","School of Software and Microelectronics, Peking University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Multimedia Information Processing, Peking University","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Software and Microelectronics, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053055634","display_name":"Jiaxing Lin","orcid":"https://orcid.org/0000-0003-3193-5522","observed_orcids":["https://orcid.org/0000-0003-3193-5522"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxing Lin","raw_affiliation_strings":["National Key Laboratory for Multimedia Information Processing, Peking University","School of Software and Microelectronics, Peking University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Multimedia Information Processing, Peking University","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Software and Microelectronics, Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021459300","display_name":"Baobao Chang","orcid":"https://orcid.org/0000-0003-2824-6750","observed_orcids":["https://orcid.org/0000-0003-2824-6750"]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baobao Chang","raw_affiliation_strings":["National Key Laboratory for Multimedia Information Processing, Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Multimedia Information Processing, Peking University","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.5303,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.62856454,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3883","last_page":"3896"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","score":0.0007999999797903001,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/remote-supervision","display_name":"distant supervision","score":0.8820000290870667},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"named entity recognition","score":0.9959999918937683},{"id":"https://openalex.org/keywords/noisy-annotations","display_name":"noisy annotations","score":0.9789999723434448},{"id":"https://openalex.org/keywords/incomplete-annotations","display_name":"incomplete annotations","score":0.9959999918937683},{"id":"https://openalex.org/keywords/entity-ambiguity","display_name":"entity ambiguity","score":0.5040000081062317}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.8156055212020874},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7580080032348633},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6817522048950195},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.6589646339416504},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6107242107391357},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5615334510803223},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4983816146850586},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.459360808134079},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4569566249847412},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3580706715583801},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09169453382492065},{"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2023.findings-acl.239","doi":"https://doi.org/10.18653/v1/2023.findings-acl.239","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-acl.239","pdf_url":"https://aclanthology.org/2023.findings-acl.239.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2023","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.findings-acl.239","doi":"https://doi.org/10.18653/v1/2023.findings-acl.239","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-acl.239","pdf_url":"https://aclanthology.org/2023.findings-acl.239.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G655826466","display_name":"\u57fa\u4e8e\u8bed\u8a00\u8ba4\u77e5\u673a\u7406\u7684\u6c49\u8bed\u6846\u67b6\u8bed\u4e49\u8ba1\u7b97\u7814\u7a76","funder_award_id":"61936012","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385570089.pdf","grobid_xml":"https://content.openalex.org/works/W4385570089.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2004763266","https://openalex.org/W2765407302","https://openalex.org/W2803187616","https://openalex.org/W2812538530","https://openalex.org/W2884561390","https://openalex.org/W2891383691","https://openalex.org/W2909793444","https://openalex.org/W2911489562","https://openalex.org/W2913520548","https://openalex.org/W2945214158","https://openalex.org/W2952087486","https://openalex.org/W2953010755","https://openalex.org/W2962902328","https://openalex.org/W2963341956","https://openalex.org/W2963697299","https://openalex.org/W2965373594","https://openalex.org/W2971071849","https://openalex.org/W3034185248","https://openalex.org/W3038098779","https://openalex.org/W3110897094","https://openalex.org/W3173682066","https://openalex.org/W3175344781","https://openalex.org/W3199289866","https://openalex.org/W3202188990","https://openalex.org/W3213836846","https://openalex.org/W3215867835","https://openalex.org/W4224244950","https://openalex.org/W4287854516","https://openalex.org/W4287855168","https://openalex.org/W4297631924","https://openalex.org/W4385567025","https://openalex.org/W4385572992","https://openalex.org/W4385574246"],"related_works":["https://openalex.org/W4410086690","https://openalex.org/W4385571128","https://openalex.org/W3199289866","https://openalex.org/W3213836846","https://openalex.org/W2945214158","https://openalex.org/W4296949274","https://openalex.org/W2983651159","https://openalex.org/W2812538530","https://openalex.org/W4289111524","https://openalex.org/W3193344699"],"abstract_inverted_index":{"Distantly-Supervised":[0],"Named":[1],"Entity":[2],"Recognition":[3],"effectively":[4],"alleviates":[5],"the":[6,14,17,22,50,58,68,78,98,126,136,139],"burden":[7],"of":[8,25,47,61,64,70,85,142],"timeconsuming":[9],"and":[10,21,30,93,106,120],"expensive":[11],"annotation":[12,32,40,119],"in":[13,73,135],"supervised":[15],"setting.But":[16],"context-free":[18],"matching":[19],"process":[20],"limited":[23],"coverage":[24],"knowledge":[26],"bases":[27],"introduce":[28],"inaccurate":[29,104],"incomplete":[31,39,118],"noise":[33,41,48,65,86,143],"respectively.Previous":[34],"studies":[35],"either":[36],"considered":[37],"only":[38],"or":[42],"indiscriminately":[43],"handle":[44,81],"two":[45,62,83,140],"types":[46,63,84,141],"with":[49,88],"same":[51],"strategy.In":[52],"this":[53],"paper,":[54],"we":[55,76,133],"argue":[56],"that":[57,138],"different":[59,71],"causes":[60],"bring":[66],"up":[67],"requirement":[69],"strategies":[72],"model":[74],"architecture.Therefore,":[75],"propose":[77],"SANTA":[79],"to":[80,96,110,124],"these":[82],"separately":[87],"(1)":[89],"Memory-smoothed":[90],"Focal":[91],"Loss":[92],"Entity-aware":[94],"KNN":[95],"relieve":[97],"entity":[99],"ambiguity":[100],"problem":[101,115],"caused":[102,116],"by":[103,117],"annotation,":[105],"(2)":[107],"Boundary":[108],"Mixup":[109],"alleviate":[111],"decision":[112],"boundary":[113],"shifting":[114],"a":[121,149],"noisetolerant":[122],"loss":[123],"improve":[125],"robustness.Benefiting":[127],"from":[128],"our":[129],"separate":[130],"tailored":[131],"strategies,":[132],"confirm":[134],"experiment":[137],"are":[144],"well":[145],"mitigated.SANTA":[146],"also":[147],"achieves":[148],"new":[150],"state-of-the-art":[151],"on":[152],"five":[153],"public":[154],"datasets.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2023-08-05T00:00:00"}