Mitigating Gender Bias Amplification in Distribution by Posterior Regularization
This work addresses gender bias in NLP for fairness and equity, representing an incremental improvement by focusing on distribution-level analysis rather than top predictions.
The paper tackled the problem of gender bias amplification in NLP models by analyzing it from a distribution perspective, showing that bias is amplified in predicted probability distributions, and proposed a posterior regularization method that nearly eliminates this amplification with minimal performance loss.
Advanced machine learning techniques have boosted the performance of natural language processing. Nevertheless, recent studies, e.g., Zhao et al. (2017) show that these techniques inadvertently capture the societal bias hidden in the corpus and further amplify it. However, their analysis is conducted only on models' top predictions. In this paper, we investigate the gender bias amplification issue from the distribution perspective and demonstrate that the bias is amplified in the view of predicted probability distribution over labels. We further propose a bias mitigation approach based on posterior regularization. With little performance loss, our method can almost remove the bias amplification in the distribution. Our study sheds the light on understanding the bias amplification.