{"id":"https://openalex.org/W2969282158","doi":"https://doi.org/10.18653/v1/d19-1107","title":"Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasets","display_name":"Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasets","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2969282158","doi":"https://doi.org/10.18653/v1/d19-1107","mag":"2969282158"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d19-1107","doi":"https://doi.org/10.18653/v1/d19-1107","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-1107","pdf_url":"https://www.aclweb.org/anthology/D19-1107.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 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","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://www.aclweb.org/anthology/D19-1107.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065717258","display_name":"Mor Geva","orcid":"https://orcid.org/0000-0001-9529-6315","observed_orcids":["https://orcid.org/0000-0001-9529-6315"]},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]},{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]}],"countries":["IL","US"],"is_corresponding":false,"raw_author_name":"Mor Geva","raw_affiliation_strings":["Allen Institute for AI","Tel Aviv University *"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Allen Institute for AI","institution_ids":["https://openalex.org/I4210156221"]},{"raw_affiliation_string":"Tel Aviv University *","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028476919","display_name":"Yoav Goldberg","orcid":"https://orcid.org/0000-0002-6497-829X","observed_orcids":["https://orcid.org/0000-0002-6497-829X"]},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]},{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]}],"countries":["IL","US"],"is_corresponding":false,"raw_author_name":"Yoav Goldberg","raw_affiliation_strings":["Allen Institute for AI","Bar-Ilan University ,","Bar-Ilan University, Ramat Gan, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Allen Institute for AI","institution_ids":["https://openalex.org/I4210156221"]},{"raw_affiliation_string":"Bar-Ilan University ,","institution_ids":["https://openalex.org/I13955877"]},{"raw_affiliation_string":"Bar-Ilan University, Ramat Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045872048","display_name":"Jonathan Berant","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]},{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]}],"countries":["IL","US"],"is_corresponding":false,"raw_author_name":"Jonathan Berant","raw_affiliation_strings":["Allen Institute for AI","Tel Aviv University *"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Allen Institute for AI","institution_ids":["https://openalex.org/I4210156221"]},{"raw_affiliation_string":"Tel Aviv University *","institution_ids":["https://openalex.org/I16391192"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":17.2113,"has_fulltext":true,"cited_by_count":337,"citation_normalized_percentile":{"value":0.99407746,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1161","last_page":"1166"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.7749000191688538,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.7749000191688538,"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":0.10750000178813934,"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":0.031199999153614044,"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/annotator-bias","display_name":"annotator bias","score":0.9919999837875366},{"id":"https://openalex.org/keywords/dataset-construction","display_name":"dataset construction","score":0.3970000147819519},{"id":"https://openalex.org/keywords/task-modeling","display_name":"task modeling","score":0.5099999904632568}],"concepts":[{"id":"https://openalex.org/C62230096","wikidata":"https://www.wikidata.org/wiki/Q275969","display_name":"Crowdsourcing","level":2,"score":0.8771673440933228},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8259519338607788},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6440860629081726},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6399085521697998},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6326942443847656},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5728030204772949},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.5284048318862915},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5000040531158447},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.4748922884464264},{"id":"https://openalex.org/C47385372","wikidata":"https://www.wikidata.org/wiki/Q7098943","display_name":"Optimal distinctiveness theory","level":2,"score":0.47346916794776917},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.47136297821998596},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.463681161403656},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.44295698404312134},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3621160387992859},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10569092631340027},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06460824608802795},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/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/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/d19-1107","doi":"https://doi.org/10.18653/v1/d19-1107","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-1107","pdf_url":"https://www.aclweb.org/anthology/D19-1107.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 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1908.07898","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1908.07898","pdf_url":"https://arxiv.org/pdf/1908.07898","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":"mag:2969282158","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1908.07898v2","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1908.07898","doi":"https://doi.org/10.48550/arxiv.1908.07898","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1908.07898","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/d19-1107","doi":"https://doi.org/10.18653/v1/d19-1107","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d19-1107","pdf_url":"https://www.aclweb.org/anthology/D19-1107.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 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322252","display_name":"Israel Science Foundation","ror":"https://ror.org/04sazxf24"},{"id":"https://openalex.org/F4320322596","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2969282158.pdf","grobid_xml":"https://content.openalex.org/works/W2969282158.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W172170795","https://openalex.org/W759515131","https://openalex.org/W1840435438","https://openalex.org/W2084413241","https://openalex.org/W2125436846","https://openalex.org/W2163361328","https://openalex.org/W2277195237","https://openalex.org/W2294343784","https://openalex.org/W2296076036","https://openalex.org/W2557764419","https://openalex.org/W2561529111","https://openalex.org/W2586358499","https://openalex.org/W2607892599","https://openalex.org/W2790415926","https://openalex.org/W2798358706","https://openalex.org/W2798617936","https://openalex.org/W2798665661","https://openalex.org/W2798935874","https://openalex.org/W2890894339","https://openalex.org/W2896457183","https://openalex.org/W2898695519","https://openalex.org/W2899335602","https://openalex.org/W2899689163","https://openalex.org/W2903073381","https://openalex.org/W2919420119","https://openalex.org/W2951365061","https://openalex.org/W2962899377","https://openalex.org/W2963323070","https://openalex.org/W2963341956","https://openalex.org/W2963748441","https://openalex.org/W2963995027","https://openalex.org/W2964207259"],"related_works":["https://openalex.org/W6978058397","https://openalex.org/W4404783774","https://openalex.org/W4200635105","https://openalex.org/W4401042461","https://openalex.org/W7160144960","https://openalex.org/W1501848909","https://openalex.org/W4412944405","https://openalex.org/W3205067036","https://openalex.org/W4386566763","https://openalex.org/W4401042630"],"abstract_inverted_index":{"Mor":[0],"Geva,":[1],"Yoav":[2],"Goldberg,":[3],"Jonathan":[4],"Berant.":[5],"Proceedings":[6],"of":[7],"the":[8,19],"2019":[9],"Conference":[10,23],"on":[11,24],"Empirical":[12],"Methods":[13],"in":[14],"Natural":[15,25],"Language":[16,26],"Processing":[17,27],"and":[18],"9th":[20],"International":[21],"Joint":[22],"(EMNLP-IJCNLP).":[28],"2019.":[29]},"counts_by_year":[{"year":2026,"cited_by_count":16},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":36},{"year":2023,"cited_by_count":54},{"year":2022,"cited_by_count":63},{"year":2021,"cited_by_count":84},{"year":2020,"cited_by_count":58},{"year":2019,"cited_by_count":6}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2019-08-29T00:00:00"}