Investigating Bias in Multilingual Language Models: Cross-Lingual Transfer of Debiasing Techniques
Authors:
Top Cited Papers
Open Access
- 1 January 2023
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 2887-2896
Abstract
Manon Reusens, Philipp Borchert, Margot Mieskes, Jochen De Weerdt, Bart Baesens. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- French CrowS-Pairs: Extending a challenge dataset for measuring social bias in masked language models to a language other than English2022
- An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models2022
- Sustainable Modular Debiasing of Language Models2021
- Stereotyping Norwegian Salmon: An Inventory of Pitfalls in Fairness Benchmark Datasets2021
- Monolingual and Multilingual Reduction of Gender Bias in Contextualized Representations2020
- CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models2020
- Towards Debiasing Sentence Representations2020
- Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection2020
- Are All Languages Created Equal in Multilingual BERT?2020
- Gender Bias in Multilingual Embeddings and Cross-Lingual Transfer2020