A Survey of Race, Racism, and Anti-Racism in NLP

被引:0
作者
Field, Anjalie [1 ]
Blodgett, Su Lin [2 ]
Waseem, Zeerak [3 ]
Tsvetkov, Yulia [4 ]
机构
[1] Carnegie Mellon Univ, Pittsburgh, PA 15213 USA
[2] Microsoft Res, Redmond, WA USA
[3] Univ Sheffield, Sheffield, S Yorkshire, England
[4] Univ Washington, Seattle, WA 98195 USA
来源
59TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 11TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING, VOL 1 (ACL-IJCNLP 2021) | 2021年
基金
美国国家科学基金会;
关键词
LANGUAGE;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Despite inextricable ties between race and language, little work has considered race in NLP research and development. In this work, we survey 79 papers from the ACL anthology that mention race. These papers reveal various types of race-related bias in all stages of NLP model development, highlighting the need for proactive consideration of how NLP systems can uphold racial hierarchies. However, persistent gaps in research on race and NLP remain: race has been siloed as a niche topic and remains ignored in many NLP tasks; most work operationalizes race as a fixed single-dimensional variable with a ground-truth label, which risks reinforcing differences produced by historical racism; and the voices of historically marginalized people are nearly absent in NLP literature. By identifying where and how NLP literature has and has not considered race, especially in comparison to related fields, our work calls for inclusion and racial justice in NLP research practices.
引用
收藏
页码:1905 / 1925
页数:21
相关论文
共 137 条
[1]  
Adams Julia, 2019, SOCIUS, V5
[2]  
Amir S., 2019, P 6 WORKSHOP COMPUTA, P114, DOI [10.18653/v1/W19-3013, DOI 10.18653/V1/W19-3013]
[3]  
Angwin J., 2022, Machine bias: There's software used across the country to predict future criminals, and it's biased against blacks, P254, DOI DOI 10.1201/9781003278290-37
[4]  
[Anonymous], 2016, P 1 WORKSH NLP COMP, P138, DOI [DOI 10.18653/V1/W16-5618, 10.18653/v1/W16-5618]
[5]  
[Anonymous], 2013, HLT-NAACL
[6]  
[Anonymous], 2017, P 2 WORKSH NLP COMP
[7]  
[Anonymous], 2018, EMNLP
[8]  
[Anonymous], 2011, P 49 ANN M ASS COMPU
[9]  
Assimakopoulos S, 2020, PROCEEDINGS OF THE 12TH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION (LREC 2020), P5088
[10]  
Bar-Tal Daniel, 2013, STEREOTYPING PREJUDI