Do clustering-based debiasing techniques maintain higher semantic textual similarity scores than projection-based methods across

In comparison to the numerous debiasing methods proposed for the static noncontextualised word embeddings, the discriminative biases in contextualised embeddings have received relatively little attention. We propose a fine-tuning method that can be applied at token-or sentence-levels to debias pre-trained contextualised embeddings. Our proposed method can be applied to any pretrained contextualised embedding model, without requiring to retrain those models. Using gender bias as an illustrative example, we then conduct a systematic study using several state-of-the-art (SoTA) contextualised repr

Research goal: Do clustering-based debiasing techniques maintain higher semantic textual similarity scores than projection-based methods across diverse domain benchmarks?

Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 8.5/10.