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 information. Understanding this dilemma provides for a useful way of rethinking the ethics of algorithmic bias in NLP.
Original language | English |
---|---|
Pages (from-to) | 1-28 |
Number of pages | 28 |
Journal | Feminist Philosophy Quarterly |
Volume | 8 |
Issue number | 3/4 |
DOIs | |
Publication status | Published - 21 Dec 2022 |
Bibliographical note
Copyright the Author(s) 2022. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.Keywords
- artificial intelligence
- algorithms
- bias