Obserwuj
Ewoenam Kwaku Tokpo
Ewoenam Kwaku Tokpo
Zweryfikowany adres z uantwerpen.be - Strona główna
Tytuł
Cytowane przez
Cytowane przez
Rok
Measuring fairness with biased rulers: A comparative study on bias metrics for pre-trained language models
P Delobelle, EK Tokpo, T Calders, B Berendt
Proceedings of the 2022 Conference of the North American chapter of the …, 2022
1212022
Text style transfer for bias mitigation using masked language modeling
EK Tokpo, T Calders
In Proceedings of the 2022 Conference of the North American Chapter of the …, 2022
382022
Measuring fairness with biased rulers: A survey on quantifying biases in pretrained language models
P Delobelle, EK Tokpo, T Calders, B Berendt
arXiv preprint arXiv:2112.07447, 2021
242021
How Far Can It Go? On Intrinsic Gender Bias Mitigation for Text Classification
E Tokpo, P Delobelle, B Berendt, T Calders
In Proceedings of the 17th Conference of the European Chapter of the …, 2023
152023
FairFlow: An Automated Approach to Model-Based Counterfactual Data Augmentation for NLP
EK Tokpo, T Calders
Joint European Conference on Machine Learning and Knowledge Discovery in …, 2024
12024
Model-based Counterfactual Generator for Gender Bias Mitigation
EK Tokpo, T Calders
arXiv preprint arXiv:2311.03186, 2023
12023
Assessing and mitigating bias in natural language systems
EK Tokpo
University of Antwerp, 2024
2024
Nie można teraz wykonać tej operacji. Spróbuj ponownie później.
Prace 1–7