Debiasing Embeddings for Reduced Gender Bias in Text Classification
This addresses bias in AI systems for fairness in applications like hiring, but it is incremental as it builds on prior debiasing methods.
The paper tackled the problem of gender bias in pretrained word embeddings affecting downstream classification tasks, specifically occupation classification, and found that traditional debiasing techniques can worsen bias but a minor adjustment reduces bias while maintaining high accuracy.
(Bolukbasi et al., 2016) demonstrated that pretrained word embeddings can inherit gender bias from the data they were trained on. We investigate how this bias affects downstream classification tasks, using the case study of occupation classification (De-Arteaga et al.,2019). We show that traditional techniques for debiasing embeddings can actually worsen the bias of the downstream classifier by providing a less noisy channel for communicating gender information. With a relatively minor adjustment, however, we show how these same techniques can be used to simultaneously reduce bias and maintain high classification accuracy.