{"id":"https://openalex.org/W3191132518","doi":"https://doi.org/10.1145/3461702.3462530","title":"Gender Bias and Under-Representation in Natural Language Processing Across Human Languages","display_name":"Gender Bias and Under-Representation in Natural Language Processing Across Human Languages","publication_year":2021,"publication_date":"2021-07-21","ids":{"openalex":"https://openalex.org/W3191132518","doi":"https://doi.org/10.1145/3461702.3462530","mag":"3191132518"},"language":"en","primary_location":{"id":"doi:10.1145/3461702.3462530","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3461702.3462530","pdf_url":null,"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":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100378066","display_name":"Yan Chen","orcid":"https://orcid.org/0000-0002-2082-9639"},"institutions":[{"id":"https://openalex.org/I16944753","display_name":"Clarkson University","ror":"https://ror.org/03rwgpn18","country_code":"US","type":"education","lineage":["https://openalex.org/I16944753"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yan Chen","raw_affiliation_strings":["Clarkson University, Potsdam, NY, USA"],"affiliations":[{"raw_affiliation_string":"Clarkson University, Potsdam, NY, USA","institution_ids":["https://openalex.org/I16944753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071380702","display_name":"Christopher Mahoney","orcid":null},"institutions":[{"id":"https://openalex.org/I16944753","display_name":"Clarkson University","ror":"https://ror.org/03rwgpn18","country_code":"US","type":"education","lineage":["https://openalex.org/I16944753"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Mahoney","raw_affiliation_strings":["Clarkson University, Potsdam, NY, USA"],"affiliations":[{"raw_affiliation_string":"Clarkson University, Potsdam, NY, USA","institution_ids":["https://openalex.org/I16944753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076212459","display_name":"Isabella Grasso","orcid":"https://orcid.org/0000-0002-4829-3776"},"institutions":[{"id":"https://openalex.org/I16944753","display_name":"Clarkson University","ror":"https://ror.org/03rwgpn18","country_code":"US","type":"education","lineage":["https://openalex.org/I16944753"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Isabella Grasso","raw_affiliation_strings":["Clarkson University, Potsdam, NY, USA"],"affiliations":[{"raw_affiliation_string":"Clarkson University, Potsdam, NY, USA","institution_ids":["https://openalex.org/I16944753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010621136","display_name":"Esma Wali","orcid":null},"institutions":[{"id":"https://openalex.org/I16944753","display_name":"Clarkson University","ror":"https://ror.org/03rwgpn18","country_code":"US","type":"education","lineage":["https://openalex.org/I16944753"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Esma Wali","raw_affiliation_strings":["Clarkson University, Potsdam , NY, USA"],"affiliations":[{"raw_affiliation_string":"Clarkson University, Potsdam , NY, USA","institution_ids":["https://openalex.org/I16944753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103041186","display_name":"Abigail Matthews","orcid":"https://orcid.org/0000-0002-5313-231X"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abigail Matthews","raw_affiliation_strings":["University of Wisconsin, Madison, WI, USA"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111829032","display_name":"Thomas Middleton","orcid":null},"institutions":[{"id":"https://openalex.org/I16944753","display_name":"Clarkson University","ror":"https://ror.org/03rwgpn18","country_code":"US","type":"education","lineage":["https://openalex.org/I16944753"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas Middleton","raw_affiliation_strings":["Clarkson University, Potsdam, NY, USA"],"affiliations":[{"raw_affiliation_string":"Clarkson University, Potsdam, NY, USA","institution_ids":["https://openalex.org/I16944753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005229152","display_name":"Mariama Njie","orcid":null},"institutions":[{"id":"https://openalex.org/I173466955","display_name":"Iona College","ror":"https://ror.org/00m79dm66","country_code":"US","type":"education","lineage":["https://openalex.org/I173466955"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mariama Njie","raw_affiliation_strings":["Iona College, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Iona College, New York, NY, USA","institution_ids":["https://openalex.org/I173466955"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070197299","display_name":"Jeanna Matthews","orcid":"https://orcid.org/0000-0001-5955-0996"},"institutions":[{"id":"https://openalex.org/I16944753","display_name":"Clarkson University","ror":"https://ror.org/03rwgpn18","country_code":"US","type":"education","lineage":["https://openalex.org/I16944753"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeanna Matthews","raw_affiliation_strings":["Clarkson University, Potsdam, NY, USA"],"affiliations":[{"raw_affiliation_string":"Clarkson University, Potsdam, NY, USA","institution_ids":["https://openalex.org/I16944753"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100378066"],"corresponding_institution_ids":["https://openalex.org/I16944753"],"apc_list":null,"apc_paid":null,"fwci":3.4991,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.93784837,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"24","last_page":"34"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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":0.9987999796867371,"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/T13629","display_name":"Text Readability and Simplification","score":0.9954000115394592,"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":0.9944999814033508,"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/grammatical-gender","display_name":"Grammatical gender","score":0.7876006364822388},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7469371557235718},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7158792614936829},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6614177227020264},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.5811299085617065},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.556777834892273},{"id":"https://openalex.org/keywords/urdu","display_name":"Urdu","score":0.5484333038330078},{"id":"https://openalex.org/keywords/coreference","display_name":"Coreference","score":0.48075100779533386},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4758560359477997},{"id":"https://openalex.org/keywords/noun","display_name":"Noun","score":0.41641467809677124},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.4119090437889099}],"concepts":[{"id":"https://openalex.org/C192420165","wikidata":"https://www.wikidata.org/wiki/Q162378","display_name":"Grammatical gender","level":3,"score":0.7876006364822388},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7469371557235718},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7158792614936829},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6614177227020264},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.5811299085617065},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.556777834892273},{"id":"https://openalex.org/C2777350258","wikidata":"https://www.wikidata.org/wiki/Q1617","display_name":"Urdu","level":2,"score":0.5484333038330078},{"id":"https://openalex.org/C28076734","wikidata":"https://www.wikidata.org/wiki/Q63087","display_name":"Coreference","level":3,"score":0.48075100779533386},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4758560359477997},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.41641467809677124},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.4119090437889099},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3461702.3462530","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3461702.3462530","pdf_url":null,"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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2483215953","https://openalex.org/W2788481061","https://openalex.org/W2950577311","https://openalex.org/W2963341956","https://openalex.org/W3023547440","https://openalex.org/W3105935311","https://openalex.org/W3131247433"],"related_works":["https://openalex.org/W4253655968","https://openalex.org/W4361305524","https://openalex.org/W2172171638","https://openalex.org/W4248979949","https://openalex.org/W4288087827","https://openalex.org/W2982560432","https://openalex.org/W2024868677","https://openalex.org/W3000132975","https://openalex.org/W2987120287","https://openalex.org/W2104410829"],"abstract_inverted_index":{"Natural":[0],"Language":[1],"Processing":[2],"(NLP)":[3],"systems":[4,14,24],"are":[5,121],"at":[6],"the":[7,72,80,92,103,111,117,177],"heart":[8],"of":[9,29,49,68,113,189],"many":[10,95],"critical":[11],"automated":[12],"decision-making":[13],"making":[15],"crucial":[16,89],"recommendations":[17],"about":[18],"our":[19,86,123],"future":[20],"world.":[21],"However,":[22],"these":[23,76,172],"reflect":[25],"a":[26,35,45],"wide":[27],"range":[28],"biases,":[30],"from":[31],"gender":[32,69,133,173],"bias":[33,36,70,134,174],"to":[34,129,144],"in":[37,71,91,100,116,180],"which":[38],"voices":[39,115],"they":[40],"represent.":[41],"In":[42,79],"this":[43],"paper,":[44],"team":[46],"including":[47,148,162],"speakers":[48],"9":[50,77],"languages":[51,149,182],"-":[52,63],"Chinese,":[53],"Spanish,":[54,151],"English,":[55],"Arabic,":[56,152],"German,":[57,153],"French,":[58],"Farsi,":[59],"Urdu,":[60],"and":[61,65,108,131,141,155,166],"Wolof":[62],"reports":[64],"analyzes":[66],"measurements":[67,175],"Wikipedia":[73,178],"corpora":[74,179,188],"for":[75,94,139],"languages.":[78,96],"process,":[81],"we":[82],"also":[83],"document":[84],"how":[85],"work":[87],"exposes":[88],"gaps":[90],"NLP-pipeline":[93,105],"Despite":[97],"substantial":[98],"investments":[99],"multilingual":[101],"support,":[102],"modern":[104],"still":[106],"systematically":[107],"dramatically":[109],"under-represents":[110],"majority":[112],"human":[114],"NLP-guided":[118],"decisions":[119],"that":[120,157],"shaping":[122],"collective":[124],"future.":[125],"We":[126,170],"develop":[127],"extensions":[128],"profession-level":[130],"corpus-level":[132],"metric":[135],"calculations":[136],"originally":[137],"designed":[138],"English":[140],"apply":[142],"them":[143],"8":[145],"other":[146],"languages,":[147],"like":[150],"French":[154],"Urdu":[156],"have":[158],"grammatically":[159],"gendered":[160],"nouns":[161],"different":[163,181],"feminine,":[164],"masculine":[165],"neuter":[167],"profession":[168],"words.":[169],"compare":[171],"across":[176,186],"as":[183,185],"well":[184],"some":[187],"more":[190],"traditional":[191],"literature.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}