Unpacking the Interdependent Systems of Discrimination: Ableist Bias in NLP Systems through an Intersectional Lens

Unpacking the Interdependent Systems of Discrimination: Ableist Bias in NLP Systems through an Intersectional Lens

Much of the world's population experiences some form of disability during their lifetime. Caution must be exercised while designing natural language processing (NLP) systems to prevent systems from inadvertently perpetuating ableist bias against people with disabilities, i.e., prejudice that fa...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Hassan, Saad, Huenerfauth, Matt, Alm, Cecilia Ovesdotter
Format: Artikel
Sprache:eng
Schlagworte:
Computer Science - Artificial Intelligence
Computer Science - Computation and Language
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Hassan, Saad
Huenerfauth, Matt
Alm, Cecilia Ovesdotter
description Much of the world's population experiences some form of disability during their lifetime. Caution must be exercised while designing natural language processing (NLP) systems to prevent systems from inadvertently perpetuating ableist bias against people with disabilities, i.e., prejudice that favors those with typical abilities. We report on various analyses based on word predictions of a large-scale BERT language model. Statistically significant results demonstrate that people with disabilities can be disadvantaged. Findings also explore overlapping forms of discrimination related to interconnected gender and race identities.
doi_str_mv 10.48550/arxiv.2110.00521
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2110_00521</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2110_00521</sourcerecordid><originalsourceid>FETCH-LOGICAL-a671-1141bc19015daa14c061f833bf0a7e147510859b3b999b5f647638c9528537c53</originalsourceid><addsrcrecordid>eNo9j8tOwzAURL1hgQofwAr_QIpvbCcxu1JelSJAoqyja8dpLFInsg2if08fiNVIo5nRHEKugM1FJSW7wfDjvuc57A3GZA7nJHz4Cc2n8xuaektXPtnQ2sn61vpE33cx2W2kY0fvXTTBbZ3H5EZ_Sxd6sC4meucwUufpS_32H099GL82PUV_GozWHEo40Nr6eEHOOhyivfzTGVk_PqyXz1n9-rRaLuoMixIyAAHagGIgW0QQhhXQVZzrjmFpQZQSWCWV5loppWVXiLLglVEyryQvjeQzcn2aPUI30_48hl1zgG-O8PwXa49UwQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Unpacking the Interdependent Systems of Discrimination: Ableist Bias in NLP Systems through an Intersectional Lens</title><source>arXiv.org</source><creator>Hassan, Saad ; Huenerfauth, Matt ; Alm, Cecilia Ovesdotter</creator><creatorcontrib>Hassan, Saad ; Huenerfauth, Matt ; Alm, Cecilia Ovesdotter</creatorcontrib><description>Much of the world's population experiences some form of disability during their lifetime. Caution must be exercised while designing natural language processing (NLP) systems to prevent systems from inadvertently perpetuating ableist bias against people with disabilities, i.e., prejudice that favors those with typical abilities. We report on various analyses based on word predictions of a large-scale BERT language model. Statistically significant results demonstrate that people with disabilities can be disadvantaged. Findings also explore overlapping forms of discrimination related to interconnected gender and race identities.</description><identifier>DOI: 10.48550/arxiv.2110.00521</identifier><language>eng</language><subject>Computer Science - Artificial Intelligence ; Computer Science - Computation and Language</subject><creationdate>2021-10</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,781,886</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2110.00521$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2110.00521$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Hassan, Saad</creatorcontrib><creatorcontrib>Huenerfauth, Matt</creatorcontrib><creatorcontrib>Alm, Cecilia Ovesdotter</creatorcontrib><title>Unpacking the Interdependent Systems of Discrimination: Ableist Bias in NLP Systems through an Intersectional Lens</title><description>Much of the world's population experiences some form of disability during their lifetime. Caution must be exercised while designing natural language processing (NLP) systems to prevent systems from inadvertently perpetuating ableist bias against people with disabilities, i.e., prejudice that favors those with typical abilities. We report on various analyses based on word predictions of a large-scale BERT language model. Statistically significant results demonstrate that people with disabilities can be disadvantaged. Findings also explore overlapping forms of discrimination related to interconnected gender and race identities.</description><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Computation and Language</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNo9j8tOwzAURL1hgQofwAr_QIpvbCcxu1JelSJAoqyja8dpLFInsg2if08fiNVIo5nRHEKugM1FJSW7wfDjvuc57A3GZA7nJHz4Cc2n8xuaektXPtnQ2sn61vpE33cx2W2kY0fvXTTBbZ3H5EZ_Sxd6sC4meucwUufpS_32H099GL82PUV_GozWHEo40Nr6eEHOOhyivfzTGVk_PqyXz1n9-rRaLuoMixIyAAHagGIgW0QQhhXQVZzrjmFpQZQSWCWV5loppWVXiLLglVEyryQvjeQzcn2aPUI30_48hl1zgG-O8PwXa49UwQ</recordid><startdate>20211001</startdate><enddate>20211001</enddate><creator>Hassan, Saad</creator><creator>Huenerfauth, Matt</creator><creator>Alm, Cecilia Ovesdotter</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20211001</creationdate><title>Unpacking the Interdependent Systems of Discrimination: Ableist Bias in NLP Systems through an Intersectional Lens</title><author>Hassan, Saad ; Huenerfauth, Matt ; Alm, Cecilia Ovesdotter</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a671-1141bc19015daa14c061f833bf0a7e147510859b3b999b5f647638c9528537c53</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Computation and Language</topic><toplevel>online_resources</toplevel><creatorcontrib>Hassan, Saad</creatorcontrib><creatorcontrib>Huenerfauth, Matt</creatorcontrib><creatorcontrib>Alm, Cecilia Ovesdotter</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Hassan, Saad</au><au>Huenerfauth, Matt</au><au>Alm, Cecilia Ovesdotter</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Unpacking the Interdependent Systems of Discrimination: Ableist Bias in NLP Systems through an Intersectional Lens</atitle><date>2021-10-01</date><risdate>2021</risdate><abstract>Much of the world's population experiences some form of disability during their lifetime. Caution must be exercised while designing natural language processing (NLP) systems to prevent systems from inadvertently perpetuating ableist bias against people with disabilities, i.e., prejudice that favors those with typical abilities. We report on various analyses based on word predictions of a large-scale BERT language model. Statistically significant results demonstrate that people with disabilities can be disadvantaged. Findings also explore overlapping forms of discrimination related to interconnected gender and race identities.</abstract><doi>10.48550/arxiv.2110.00521</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2110.00521
ispartof
issn
language eng
recordid cdi_arxiv_primary_2110_00521
source arXiv.org
subjects Computer Science - Artificial Intelligence
Computer Science - Computation and Language
title Unpacking the Interdependent Systems of Discrimination: Ableist Bias in NLP Systems through an Intersectional Lens
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-17T17%3A41%3A55IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Unpacking%20the%20Interdependent%20Systems%20of%20Discrimination:%20Ableist%20Bias%20in%20NLP%20Systems%20through%20an%20Intersectional%20Lens&rft.au=Hassan,%20Saad&rft.date=2021-10-01&rft_id=info:doi/10.48550/arxiv.2110.00521&rft_dat=%3Carxiv_GOX%3E2110_00521%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true