{"id":"https://openalex.org/W4416037083","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.144","title":"NUTMEG: Separating Signal From Noise in Annotator Disagreement","display_name":"NUTMEG: Separating Signal From Noise in Annotator Disagreement","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416037083","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.144"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.144","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.144","pdf_url":"https://aclanthology.org/2025.emnlp-main.144.pdf","source":null,"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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.144.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111084104","display_name":"Jonathan Ivey","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2802946424","display_name":"Johns Hopkins University Applied Physics Laboratory","ror":"https://ror.org/029pp9z10","country_code":"US","type":"facility","lineage":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jonathan Ivey","raw_affiliation_strings":["Johns Hopkins University University of Arkansas University of Michigan"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University University of Arkansas University of Michigan","institution_ids":["https://openalex.org/I2802946424","https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032138644","display_name":"Susan Gauch","orcid":"https://orcid.org/0000-0001-5538-7343"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2802946424","display_name":"Johns Hopkins University Applied Physics Laboratory","ror":"https://ror.org/029pp9z10","country_code":"US","type":"facility","lineage":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Susan Gauch","raw_affiliation_strings":["Johns Hopkins University University of Arkansas University of Michigan"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University University of Arkansas University of Michigan","institution_ids":["https://openalex.org/I2802946424","https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046126345","display_name":"David Jurgens","orcid":"https://orcid.org/0000-0002-2135-9878"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I2802946424","display_name":"Johns Hopkins University Applied Physics Laboratory","ror":"https://ror.org/029pp9z10","country_code":"US","type":"facility","lineage":["https://openalex.org/I145311948","https://openalex.org/I2802946424"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Jurgens","raw_affiliation_strings":["Johns Hopkins University University of Arkansas University of Michigan"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University University of Arkansas University of Michigan","institution_ids":["https://openalex.org/I2802946424","https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5111084104"],"corresponding_institution_ids":["https://openalex.org/I145311948","https://openalex.org/I2802946424"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.3558526,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2874","last_page":"2887"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.423799991607666,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.423799991607666,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.06989999860525131,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.06960000097751617,"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/noise","display_name":"Noise (video)","score":0.6064000129699707},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5493999719619751},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.39259999990463257},{"id":"https://openalex.org/keywords/detection-theory","display_name":"Detection theory","score":0.319599986076355},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.3156999945640564},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"Signal-to-noise ratio (imaging)","score":0.3082999885082245}],"concepts":[{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6064000129699707},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5493999719619751},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.45579999685287476},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4341999888420105},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.39259999990463257},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.3822999894618988},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33399999141693115},{"id":"https://openalex.org/C137270730","wikidata":"https://www.wikidata.org/wiki/Q120811","display_name":"Detection theory","level":3,"score":0.319599986076355},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3082999885082245},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.30550000071525574},{"id":"https://openalex.org/C94727143","wikidata":"https://www.wikidata.org/wiki/Q485394","display_name":"Analytic signal","level":4,"score":0.30309998989105225},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2971000075340271},{"id":"https://openalex.org/C97855336","wikidata":"https://www.wikidata.org/wiki/Q2285125","display_name":"Signal averaging","level":5,"score":0.295199990272522},{"id":"https://openalex.org/C207658827","wikidata":"https://www.wikidata.org/wiki/Q1999781","display_name":"Stochastic resonance","level":4,"score":0.2526000142097473}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.144","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.144","pdf_url":"https://aclanthology.org/2025.emnlp-main.144.pdf","source":null,"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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:scholarworks.uark.edu:dtscuht-1019","is_oa":true,"landing_page_url":"https://scholarworks.uark.edu/dtscuht/14","pdf_url":null,"source":{"id":"https://openalex.org/S2764830181","display_name":"Journal of the Arkansas Academy of Science","issn_l":"2326-0491","issn":["2326-0491","2326-0505"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320103","host_organization_name":"Arkansas Academy of Science","host_organization_lineage":["https://openalex.org/P4310320103"],"host_organization_lineage_names":["Arkansas Academy of Science"],"type":"journal"},"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data Science Undergraduate Honors Theses","raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.144","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.144","pdf_url":"https://aclanthology.org/2025.emnlp-main.144.pdf","source":null,"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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2603180164","display_name":null,"funder_award_id":"IIS-2143529","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4156043112","display_name":null,"funder_award_id":"1946391","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7470362337","display_name":null,"funder_award_id":"OIA-1946391","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416037083.pdf","grobid_xml":"https://content.openalex.org/works/W4416037083.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"NLP":[0],"models":[1,68,131,138],"often":[2],"rely":[3],"on":[4,133,140,183],"human-labeled":[5,96,184],"data":[6,14,98,135,141],"for":[7,48,174],"training":[8,97,182],"and":[9,25,56,71,104,126,158,178],"evaluation.Many":[10],"approaches":[11],"crowdsource":[12],"this":[13,76],"from":[15,95,117,142],"a":[16,81],"large":[17],"number":[18],"of":[19,156,160,165,172],"annotators":[20,51],"with":[21,119],"varying":[22],"skills,":[23],"backgrounds,":[24],"motivations,":[26],"resulting":[27],"in":[28,73,152],"conflicting":[29],"annotations.These":[30],"conflicts":[31],"have":[32,53],"traditionally":[33,143],"been":[34],"resolved":[35],"by":[36],"aggregation":[37,124,144],"methods":[38],"that":[39,47,57,85,109,129],"assume":[40],"disagreements":[41,55,180],"are":[42],"errors.Recent":[43],"work":[44],"has":[45],"argued":[46],"many":[49],"tasks":[50],"may":[52],"genuine":[54],"variation":[58],"should":[59],"be":[60],"treated":[61],"as":[62],"signal":[63,70],"rather":[64],"than":[65,122],"noise.However,":[66],"few":[67],"separate":[69],"noise":[72],"annotator":[74,89,176],"disagreement.In":[75],"work,":[77],"we":[78,107,127],"introduce":[79],"NUTMEG,":[80],"new":[82],"Bayesian":[83],"model":[84],"incorporates":[86],"information":[87],"about":[88],"backgrounds":[90],"to":[91],"remove":[92],"noisy":[93],"annotations":[94,118],"while":[99],"preserving":[100],"systematic":[101,120,179],"disagreements.Using":[102],"synthetic":[103],"real-world":[105],"data,":[106],"show":[108],"NUTMEG":[110],"is":[111],"more":[112],"effective":[113],"at":[114],"recovering":[115],"ground-truth":[116],"disagreement":[121],"traditional":[123],"methods,":[125],"demonstrate":[128],"downstream":[130],"trained":[132,139],"NUT-MEG-aggregated":[134],"significantly":[136],"outperform":[137],"methods.We":[145],"provide":[146],"further":[147],"analysis":[148],"characterizing":[149],"how":[150],"differences":[151],"subpopulation":[153],"sizes,":[154],"rates":[155,159],"disagreement,":[157],"spam":[161],"affect":[162],"the":[163,170],"performance":[164],"our":[166],"model.Our":[167],"results":[168],"highlight":[169],"importance":[171],"accounting":[173],"both":[175],"competence":[177],"when":[181],"data.":[185]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-11-08T00:00:00"}