In this paper, we provide a holistic analysis of the different sources of bias, Upstream, Sample and Overampflication biases, in NLP models. We investigate how they impact the fairness of the task of text classification. We also investigate the impact of removing these biases using different debiasing techniques on the fairness of text classification. We found that overamplification bias is the most impactful bias on the fairness of text classification. And that removing overamplification bias by fine-tuning the LM models on a dataset with balanced representations of the different identity groups leads to fairer text classification models. Finally, we build on our findings and introduce practical guidelines on how to have a fairer text classification model.

翻译：本文对NLP模型中的不同偏见来源——上游偏见、样本偏见和过度放大偏见——进行了全面分析。我们研究了这些偏见如何影响文本分类任务的公平性，并探讨了通过不同去偏技术消除这些偏见对文本分类公平性的影响。研究发现，过度放大偏见是对文本分类公平性影响最大的偏见因素，而通过在具有不同身份群体平衡表示的数据集上微调LM模型来消除过度放大偏见，可以训练出更公平的文本分类模型。最后，我们基于研究发现，提出了关于如何构建更公平文本分类模型的实践指南。