2022
DOI: 10.5206/fpq/2022.3/4.14292
|View full text |Cite
|
Sign up to set email alerts
|

Bias Dilemma

Oisín Deery,
Katherine Bailey

Abstract: Addressing biases in natural-language processing (NLP) systems presents an underappreciated ethical dilemma, which we think underlies recent debates about bias in NLP models. In brief, even if we could eliminate bias from language models or their outputs, we would thereby often withhold descriptively or ethically useful information, despite avoiding perpetuating or amplifying bias. Yet if we do not debias, we can perpetuate or amplify bias, even if we retain relevant descriptively or ethically useful informati… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

0
0
0

Year Published

2023
2023
2023
2023

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
references
References 19 publications
0
0
0
Order By: Relevance