Mitigating Gender Bias Amplification in Distribution by Posterior Regularization

By Shengyu Jia, Tao Meng, Jieyu Zhao, Kai-Wei Chang. 2020

46 citations recorded by the source corpus.

Advanced machine learning techniques have boosted the performance of natural language processing. Nevertheless, recent studies, e.g., (CITATION) 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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Language (Technology) is Power: A Critical Survey of “Bias” in NLP (2020, neutral): “…(2019); Prates et al. (2019); Prost et al. (2019); Qian et al. (2019); Swinger et al. (2019); Zhao et al. (2019); Zhou et al. (2019); Ethayarajh (2020); Huang et al. (2020); Jia et al. (2020); Popović et al. (2020); Pryzant et al. (2020); Vig et al. (2020); Wang et al. (2020); Zhao et al. (2020).”
Directional Bias Amplification (2021, methodology): “Bias amplification has been measured by looking at binary classifications without attributes (Leino et al., 2019), GANs (Jain et al., 2020; Choi et al., 2020), and correlations (Zhao et al., 2017; Jia et al., 2020).”
Bias and Fairness in Large Language Models: A Survey (2023, methodology): “To calibrate the predicted probability distribution to avoid amplification, Jia et al. (2020) propose a regularization approach to constrain the posterior distribution to match the original label distribution.”
Theories of “Gender” in NLP Bias Research (2022, unknown): “14497 [68] Shengyu Jia, Tao Meng, Jieyu Zhao, and Kai-Wei Chang.”
A Systematic Study of Bias Amplification (2022, methodology): “Prior work has measured bias amplification using generative adversarial networks [8, 22], by considering binary classifications without attributes [28], and by measuring correlations in model predictions [23, 47].”
Quantifying Societal Bias Amplification in Image Captioning (2022, unknown): “With an increased interest in fairness, multiple methods for mitigating the effects of dataset bias have been proposed [19, 32, 39, 40, 47].”
Gender bias and stereotypes in Large Language Models (2023, background): “…effect for women, such that stereotypically male occupations were chosen less frequently than expected and stereotypically female occupations were chosen more frequently than expected — that is, the model amplifies stereotypical biases about women’s occupations [8, 10, 37, 39, 54, 88, 101, 103].”