Effectiveness of Debiasing Techniques: An Indigenous Qualitative Analysis

Vithya Yogarajan*, Gillian Dobbie, Henry Gouk

*Corresponding author for this work

Research output: Contribution to conferenceAbstractpeer-review

Abstract / Description of output

An indigenous perspective on the effectiveness of debiasing techniques for pre-trained language models (PLMs) is presented in this paper. The current techniques used to measure and debias PLMs are skewed towards the US racial biases and rely on pre-defined bias attributes (e.g. "black" vs "white"). Some require large datasets and further pre-training. Such techniques are not designed to capture the underrepresented indigenous populations in other countries, such as Māori in New Zealand. Local knowledge and understanding must be incorporated to ensure unbiased algorithms, especially when addressing a resource-restricted society.
Original languageEnglish
Pages1-5
Publication statusPublished - 1 May 2023
EventThe Eleventh International Conference on Learning Representations - Kigali, Rwanda
Duration: 1 May 20235 May 2023
https://iclr.cc/Conferences/2023

Conference

ConferenceThe Eleventh International Conference on Learning Representations
Abbreviated titleICLR 2023
Country/TerritoryRwanda
CityKigali
Period1/05/235/05/23
Internet address

Fingerprint

Dive into the research topics of 'Effectiveness of Debiasing Techniques: An Indigenous Qualitative Analysis'. Together they form a unique fingerprint.

Cite this