{"id":"https://openalex.org/W4389518984","doi":"https://doi.org/10.18653/v1/2023.findings-emnlp.355","title":"Don\u2019t waste a single annotation: improving single-label classifiers through soft labels","display_name":"Don\u2019t waste a single annotation: improving single-label classifiers through soft labels","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4389518984","doi":"https://doi.org/10.18653/v1/2023.findings-emnlp.355"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.findings-emnlp.355","doi":"https://doi.org/10.18653/v1/2023.findings-emnlp.355","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-emnlp.355","pdf_url":"https://aclanthology.org/2023.findings-emnlp.355.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"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: EMNLP 2023","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.findings-emnlp.355.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ben Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ben Wu","raw_affiliation_strings":["Department of Computer Science, The University of Sheffield, Sheffield, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100387780","display_name":"Yue Li","orcid":"https://orcid.org/0000-0002-2654-1580","observed_orcids":["https://orcid.org/0000-0002-2654-1580","https://orcid.org/0009-0008-7953-5062","https://orcid.org/0000-0001-5936-3437"]},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yue Li","raw_affiliation_strings":["Department of Computer Science, The University of Sheffield, Sheffield, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113159165","display_name":"Yida Mu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yida Mu","raw_affiliation_strings":["Department of Computer Science, The University of Sheffield, Sheffield, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065368839","display_name":"Carolina Scarton","orcid":"https://orcid.org/0000-0002-0103-4072","observed_orcids":["https://orcid.org/0000-0002-0103-4072"]},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Carolina Scarton","raw_affiliation_strings":["Department of Computer Science, The University of Sheffield, Sheffield, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021952588","display_name":"Kalina Bontcheva","orcid":"https://orcid.org/0000-0001-6152-9600","observed_orcids":["https://orcid.org/0000-0001-6152-9600"]},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kalina Bontcheva","raw_affiliation_strings":["Department of Computer Science, The University of Sheffield, Sheffield, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019126151","display_name":"Xingyi Song","orcid":"https://orcid.org/0000-0002-4188-6974","observed_orcids":["https://orcid.org/0000-0002-4188-6974"]},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xingyi Song","raw_affiliation_strings":["Department of Computer Science, The University of Sheffield, Sheffield, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":null,"apc_paid":null,"fwci":1.1687,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.82909696,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5347","last_page":"5355"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9613999724388123,"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":0.9613999724388123,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.012199999764561653,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.006200000178068876,"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/soft-labels","display_name":"soft labels","score":0.9810000061988831},{"id":"https://openalex.org/keywords/single-label-classification","display_name":"single-label classification","score":0.9750000238418579},{"id":"https://openalex.org/keywords/annotator-disagreement","display_name":"annotator disagreement","score":0.8579999804496765},{"id":"https://openalex.org/keywords/label-ambiguity","display_name":"label ambiguity","score":0.5590000152587891},{"id":"https://openalex.org/keywords/majority-voting","display_name":"majority voting","score":0.7590000033378601},{"id":"https://openalex.org/keywords/classifier-calibration","display_name":"classifier calibration","score":0.7940000295639038}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8311430215835571},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.7546464800834656},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7346512079238892},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.6070982217788696},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6033730506896973},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5683954358100891},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5255381464958191},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.47158563137054443},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46366173028945923},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4330601096153259},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.4190274775028229},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.41383060812950134},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3739999830722809},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07546103000640869},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06347501277923584},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/2023.findings-emnlp.355","doi":"https://doi.org/10.18653/v1/2023.findings-emnlp.355","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-emnlp.355","pdf_url":"https://aclanthology.org/2023.findings-emnlp.355.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"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: EMNLP 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2311.05265","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.05265","pdf_url":"https://arxiv.org/pdf/2311.05265","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:eprints.whiterose.ac.uk:223247","doi":null,"is_oa":true,"landing_page_url":"https://eprints.whiterose.ac.uk/223247/1/2023.findings-emnlp.355.pdf","pdf_url":"https://eprints.whiterose.ac.uk/223247/1/2023.findings-emnlp.355.pdf","source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Proceedings Paper"},{"id":"doi:10.48550/arxiv.2311.05265","doi":"https://doi.org/10.48550/arxiv.2311.05265","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2311.05265","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.findings-emnlp.355","doi":"https://doi.org/10.18653/v1/2023.findings-emnlp.355","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-emnlp.355","pdf_url":"https://aclanthology.org/2023.findings-emnlp.355.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"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: EMNLP 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2151224667","display_name":"vera.ai: VERification Assisted by Artificial Intelligence","funder_award_id":"101070093","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5378839026","display_name":null,"funder_award_id":"101070093","funder_id":"https://openalex.org/F4320334322","funder_display_name":"HORIZON EUROPE Framework Programme"},{"id":"https://openalex.org/G8247028329","display_name":null,"funder_award_id":"INEA/CEF/ICT/A2020/2381686","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null},{"id":"https://openalex.org/F4320335087","display_name":"Innovate UK","ror":"https://ror.org/05ar5fy68"},{"id":"https://openalex.org/F4320335813","display_name":"Innovation and Networks Executive Agency","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389518984.pdf","grobid_xml":"https://content.openalex.org/works/W4389518984.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W9014458","https://openalex.org/W1821462560","https://openalex.org/W2146849125","https://openalex.org/W2183341477","https://openalex.org/W2250600206","https://openalex.org/W2251089262","https://openalex.org/W2251818274","https://openalex.org/W2254249950","https://openalex.org/W2891672860","https://openalex.org/W2908510526","https://openalex.org/W2946809241","https://openalex.org/W2969769592","https://openalex.org/W2970971581","https://openalex.org/W2979826702","https://openalex.org/W3033077667","https://openalex.org/W3092614566","https://openalex.org/W3098467034","https://openalex.org/W3115922968","https://openalex.org/W3166716308","https://openalex.org/W3184904351","https://openalex.org/W3206428286","https://openalex.org/W4200444669","https://openalex.org/W4200635105","https://openalex.org/W4294969213","https://openalex.org/W4306694236","https://openalex.org/W4324148013","https://openalex.org/W4380302074","https://openalex.org/W4385573072"],"related_works":["https://openalex.org/W4417210210","https://openalex.org/W7161958820","https://openalex.org/W4283837927","https://openalex.org/W3166716308","https://openalex.org/W1862146769","https://openalex.org/W4414581705","https://openalex.org/W7055424882","https://openalex.org/W4411144125","https://openalex.org/W2606084229","https://openalex.org/W4385570315"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,6,55,63,70,75,125],"limitations":[4],"of":[5,67,87],"common":[7],"data":[8,71],"annotation":[9],"and":[10,33,65,102,122],"training":[11],"methods":[12],"for":[13,30,89],"objective":[14],"single-label":[15],"classification":[16],"tasks.Typically,":[17],"in":[18,69],"such":[19,78,97],"tasks":[20],"annotators":[21],"are":[22],"only":[23],"asked":[24],"to":[25,62,107,119],"provide":[26],"a":[27,39],"single":[28],"label":[29,42,57,83,101,127],"each":[31],"sample":[32],"annotator":[34,95],"disagreement":[35],"is":[36,43],"discarded":[37],"when":[38],"final":[40],"hard":[41,126],"decided":[44],"through":[45],"majority":[46],"voting.We":[47],"challenge":[48],"this":[49],"traditional":[50],"approach,":[51],"acknowledging":[52],"that":[53,93],"determining":[54],"appropriate":[56],"can":[58,104],"be":[59,105],"difficult":[60],"due":[61],"ambiguity":[64],"lack":[66],"context":[68],"samples.Rather":[72],"than":[73],"discarding":[74],"information":[76],"from":[77],"ambiguous":[79],"annotations,":[80],"our":[81],"soft":[82,110,115],"method":[84],"makes":[85],"use":[86],"them":[88],"training.Our":[90],"findings":[91],"indicate":[92],"additional":[94],"information,":[96],"as":[98],"confidence,":[99],"secondary":[100],"disagreement,":[103],"used":[106],"effectively":[108],"generate":[109],"labels.Training":[111],"classifiers":[112],"with":[113],"these":[114],"labels":[116],"then":[117],"leads":[118],"improved":[120],"performance":[121],"calibration":[123],"on":[124],"test":[128],"set.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2023-12-10T00:00:00"}