 | Up a level |
Kaneko, Masahiro and Bollegala, Danushka 
ORCID: 0000-0003-4476-7003
(2021)
Debiasing Pre-trained Contextualised Embeddings.
In: European Chapter of the Association for Computational Linguistics, 2021-4-19 - 2021-4-23, Online.
Kaneko, Masahiro and Bollegala, Danushka ORCID: 0000-0003-4476-7003
(2021)
Dictionary-based Debiasing of Pre-trained Word Embeddings.
In: European Chapter of the Association for Computational Linguistics, 2021-4-19 - 2021-4-23, Online.
Kaneko, Masahiro, Bollegala, Danushka ORCID: 0000-0003-4476-7003 and Okazaki, Naoaki
(2023)
The Impact of Debiasing on the Performance of Language Models in Downstream Tasks is Underestimated.
In: The 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, 2023-11-2 - 2023-11-4, Bali, Indonesia.
Kaneko, Masahiro and Bollegala, Danushka ORCID: 0000-0003-4476-7003
(2022)
Unmasking the Mask - Evaluating Social Biases in Masked Language Models.
.
Zhou, Yi, Kaneko, Masahiro and Bollegala, Danushka ORCID: 0000-0003-4476-7003
(2022)
<i>Sense Embeddings are also Biased</i> - Evaluating Social Biases in Static and Contextualised Sense Embeddings.
In: Annual Conference of the Association for Computational Linguistics, 2022-5-22 - 2022-5-27, Dublin, Ireland.