{"id":"https://openalex.org/W4389519087","doi":"https://doi.org/10.18653/v1/2023.emnlp-main.625","title":"Make Every Example Count: On the Stability and Utility of Self-Influence for Learning from Noisy NLP Datasets","display_name":"Make Every Example Count: On the Stability and Utility of Self-Influence for Learning from Noisy NLP Datasets","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4389519087","doi":"https://doi.org/10.18653/v1/2023.emnlp-main.625"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.emnlp-main.625","doi":"https://doi.org/10.18653/v1/2023.emnlp-main.625","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.emnlp-main.625","pdf_url":"https://aclanthology.org/2023.emnlp-main.625.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","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":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2023.emnlp-main.625.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050193193","display_name":"Irina Bejan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Irina Bejan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Artem Sokolov","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Artem Sokolov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5037657908","display_name":"Katja Filippova","orcid":"https://orcid.org/0009-0007-5308-0904","observed_orcids":["https://orcid.org/0009-0007-5308-0904"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Katja Filippova","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.9885,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.9041639,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"10107","last_page":"10121"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9746000170707703,"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":0.9746000170707703,"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":0.008799999952316284,"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":0.006899999920278788,"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/self-influence","display_name":"self-influence","score":0.8159999847412109},{"id":"https://openalex.org/keywords/noisy-training-data","display_name":"noisy training data","score":0.675000011920929},{"id":"https://openalex.org/keywords/data-cleaning","display_name":"data cleaning","score":0.9649999737739563},{"id":"https://openalex.org/keywords/data-quality","display_name":"data quality","score":0.6430000066757202},{"id":"https://openalex.org/keywords/outlier-detection","display_name":"outlier detection","score":0.593999981880188},{"id":"https://openalex.org/keywords/machine-translation","display_name":"machine translation","score":0.8690000176429749},{"id":"https://openalex.org/keywords/question-answering","display_name":"question answering","score":0.996999979019165},{"id":"https://openalex.org/keywords/text-classification","display_name":"text classification","score":0.8100000023841858}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8086488842964172},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7584313154220581},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6690657138824463},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6643693447113037},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.6191182732582092},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.6047450304031372},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5894286036491394},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5058984160423279},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4703538417816162},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4146807789802551},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2023.emnlp-main.625","doi":"https://doi.org/10.18653/v1/2023.emnlp-main.625","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.emnlp-main.625","pdf_url":"https://aclanthology.org/2023.emnlp-main.625.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","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":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2302.13959","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.13959","pdf_url":"https://arxiv.org/pdf/2302.13959","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2302.13959","doi":"https://doi.org/10.48550/arxiv.2302.13959","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2302.13959","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.emnlp-main.625","doi":"https://doi.org/10.18653/v1/2023.emnlp-main.625","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.emnlp-main.625","pdf_url":"https://aclanthology.org/2023.emnlp-main.625.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","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":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389519087.pdf","grobid_xml":"https://content.openalex.org/works/W4389519087.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W1905522558","https://openalex.org/W1992129502","https://openalex.org/W2006903949","https://openalex.org/W2168405694","https://openalex.org/W2296073425","https://openalex.org/W2551857043","https://openalex.org/W2597603852","https://openalex.org/W2605801332","https://openalex.org/W2606308499","https://openalex.org/W2612431505","https://openalex.org/W2618574054","https://openalex.org/W2626778328","https://openalex.org/W2767899794","https://openalex.org/W2805411799","https://openalex.org/W2889453388","https://openalex.org/W2903996579","https://openalex.org/W2912924812","https://openalex.org/W2916835973","https://openalex.org/W2920807444","https://openalex.org/W2949089361","https://openalex.org/W2950069022","https://openalex.org/W2950220847","https://openalex.org/W2953199126","https://openalex.org/W2962890089","https://openalex.org/W2963341956","https://openalex.org/W2963366389","https://openalex.org/W2966118729","https://openalex.org/W2975208319","https://openalex.org/W2978471258","https://openalex.org/W2981852735","https://openalex.org/W3004146535","https://openalex.org/W3006856964","https://openalex.org/W3013124892","https://openalex.org/W3034475796","https://openalex.org/W3035016936","https://openalex.org/W3035702670","https://openalex.org/W3037469196","https://openalex.org/W3088647504","https://openalex.org/W3092789060","https://openalex.org/W3100352836","https://openalex.org/W3118560954","https://openalex.org/W3152258780","https://openalex.org/W3184751871","https://openalex.org/W3207098686","https://openalex.org/W3213851456","https://openalex.org/W3215423069","https://openalex.org/W3217417806","https://openalex.org/W4224442590","https://openalex.org/W4225727438","https://openalex.org/W4283810737","https://openalex.org/W4309049281","https://openalex.org/W7126432724","https://openalex.org/W7133234081","https://openalex.org/W7133239480"],"related_works":["https://openalex.org/W4389519565","https://openalex.org/W7162753306","https://openalex.org/W4417426745","https://openalex.org/W4411119297","https://openalex.org/W3214430468","https://openalex.org/W4385570266","https://openalex.org/W6960187543","https://openalex.org/W4225468040","https://openalex.org/W4407185475","https://openalex.org/W4402672040"],"abstract_inverted_index":{"Increasingly":[0],"larger":[1],"datasets":[2],"have":[3,17],"become":[4,19],"a":[5],"standard":[6,34],"ingredient":[7],"to":[8,22,40,84,108],"advancing":[9],"the":[10,20,26,29,44,47,62],"state-of-theart":[11],"in":[12,77,95],"NLP.However,":[13],"data":[14,35,49,72,89],"quality":[15],"might":[16],"already":[18],"bottleneck":[21],"unlock":[23],"further":[24],"gains.Given":[25],"diversity":[27],"and":[28,50,82,100,111],"sizes":[30],"of":[31,43,46,52,64,68],"modern":[32],"datasets,":[33],"filtering":[36,53],"is":[37],"not":[38],"straight-forward":[39],"apply,":[41],"because":[42],"multifacetedness":[45],"harmful":[48],"elusiveness":[51],"rules":[54],"that":[55],"would":[56],"generalize":[57],"across":[58],"multiple":[59],"tasks.We":[60],"study":[61],"fitness":[63],"task-agnostic":[65],"self-influence":[66,87,109],"scores":[67],"training":[69],"examples":[70],"for":[71],"cleaning,":[73],"analyze":[74],"their":[75],"efficacy":[76],"capturing":[78],"naturally":[79],"occurring":[80],"outliers,":[81],"investigate":[83],"what":[85],"extent":[86],"based":[88],"cleaning":[90],"can":[91],"improve":[92],"downstream":[93],"performance":[94],"machine":[96],"translation,":[97],"question":[98],"answering":[99],"text":[101],"classification,":[102],"building":[103],"up":[104],"on":[105],"recent":[106],"approaches":[107],"calculation":[110],"automated":[112],"curriculum":[113],"learning.":[114]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-12-10T00:00:00"}