{"id":"https://openalex.org/W3034115845","doi":"https://doi.org/10.1145/3461702.3462536","title":"Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases","display_name":"Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases","publication_year":2021,"publication_date":"2021-07-21","ids":{"openalex":"https://openalex.org/W3034115845","doi":"https://doi.org/10.1145/3461702.3462536","mag":"3034115845"},"language":"en","primary_location":{"id":"doi:10.1145/3461702.3462536","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3461702.3462536","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3461702.3462536","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3461702.3462536","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Wei Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wei Guo","raw_affiliation_strings":["George Washington University, Washington, DC, USA"],"affiliations":[{"raw_affiliation_string":"George Washington University, Washington, DC, USA","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"last","author":{"id":null,"display_name":"Aylin Caliskan","orcid":null},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aylin Caliskan","raw_affiliation_strings":["George Washington University and Institute for Data, Democracy & Politics, Washington, DC, USA"],"affiliations":[{"raw_affiliation_string":"George Washington University and Institute for Data, Democracy & Politics, Washington, DC, USA","institution_ids":["https://openalex.org/I193531525"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I193531525"],"apc_list":null,"apc_paid":null,"fwci":9.6459,"has_fulltext":true,"cited_by_count":102,"citation_normalized_percentile":{"value":0.98375525,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"122","last_page":"133"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9973000288009644,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.992900013923645,"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/word","display_name":"Word (group theory)","score":0.6341999769210815},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5629000067710876},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5591999888420105},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.48489999771118164},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.47839999198913574},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4586000144481659},{"id":"https://openalex.org/keywords/contextualization","display_name":"Contextualization","score":0.4449999928474426},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.40630000829696655}],"concepts":[{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6341999769210815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5873000025749207},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5629000067710876},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5591999888420105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5389999747276306},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5292999744415283},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.48489999771118164},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.47839999198913574},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4586000144481659},{"id":"https://openalex.org/C2780712339","wikidata":"https://www.wikidata.org/wiki/Q5165204","display_name":"Contextualization","level":3,"score":0.4449999928474426},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.40630000829696655},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.38420000672340393},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.3596999943256378},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C76188268","wikidata":"https://www.wikidata.org/wiki/Q1783165","display_name":"Context effect","level":3,"score":0.303600013256073},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.30239999294281006},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.296999990940094},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C41426520","wikidata":"https://www.wikidata.org/wiki/Q1192065","display_name":"Point estimation","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.25540000200271606},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2551000118255615}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3461702.3462536","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3461702.3462536","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3461702.3462536","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2006.03955","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.03955","pdf_url":"https://arxiv.org/pdf/2006.03955","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"}],"best_oa_location":{"id":"doi:10.1145/3461702.3462536","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3461702.3462536","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3461702.3462536","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2021 AAAI/ACM Conference on AI, Ethics, and Society","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3034115845.pdf","grobid_xml":"https://content.openalex.org/works/W3034115845.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1566289585","https://openalex.org/W1967046314","https://openalex.org/W1971619625","https://openalex.org/W1989502613","https://openalex.org/W2010377943","https://openalex.org/W2046823848","https://openalex.org/W2066255970","https://openalex.org/W2076879021","https://openalex.org/W2088622183","https://openalex.org/W2102085635","https://openalex.org/W2112668762","https://openalex.org/W2168625136","https://openalex.org/W2250539671","https://openalex.org/W2326418226","https://openalex.org/W2491960697","https://openalex.org/W2769358515","https://openalex.org/W2882319491","https://openalex.org/W2903795157","https://openalex.org/W2909212904","https://openalex.org/W2952349219","https://openalex.org/W3035296331","https://openalex.org/W3045825772","https://openalex.org/W3095319910","https://openalex.org/W3133702157","https://openalex.org/W4231165370","https://openalex.org/W7018130121"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,11,37,41,65,74,108,114,121,135,151,155],"starting":[2],"point":[3],"that":[4,52,71,95,127],"implicit":[5],"human":[6],"biases":[7,21,51,93,102],"are":[8],"reflected":[9],"in":[10,22,39,54,79,117],"statistical":[12],"regularities":[13],"of":[14,76,99,110,113,138,154],"language,":[15],"it":[16],"is":[17],"possible":[18],"to":[19],"measure":[20,46],"English":[23,125],"static":[24],"word":[25,33,42],"embeddings.":[26],"State-of-the-art":[27],"neural":[28,80],"language":[29,81],"models":[30,82,122],"generate":[31],"dynamic":[32],"embeddings":[34],"dependent":[35],"on":[36,89,107,124],"context":[38],"which":[40],"appears.":[43],"Current":[44],"methods":[45],"pre-defined":[47],"social":[48,90],"and":[49,91,103,145],"intersectional":[50,92],"occur":[53],"contexts":[55],"defined":[56],"by":[57,83,142],"sentence":[58],"templates.":[59],"Dispensing":[60],"with":[61,150],"templates,":[62],"we":[63,128],"introduce":[64],"Contextualized":[66],"Embedding":[67],"Association":[68],"Test":[69],"(CEAT),":[70],"can":[72],"summarize":[73],"magnitude":[75,137],"overall":[77,139],"bias":[78,116,140],"incorporating":[84],"a":[85],"random-effects":[86],"model.":[87],"Experiments":[88],"show":[94],"CEAT":[96],"finds":[97],"evidence":[98],"all":[100],"tested":[101],"provides":[104],"comprehensive":[105],"information":[106],"variance":[109],"effect":[111],"magnitudes":[112],"same":[115],"different":[118],"contexts.":[119],"All":[120],"trained":[123],"corpora":[126],"study":[129],"contain":[130],"biased":[131],"representations.":[132],"GPT-2":[133],"contains":[134],"smallest":[136],"followed":[141],"GPT,":[143],"BERT,":[144],"then":[146],"ELMo,":[147],"negatively":[148],"correlating":[149],"contextualization":[152],"levels":[153],"models.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":27},{"year":2024,"cited_by_count":27},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":2}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2020-06-12T00:00:00"}