Text Style Transfer for Bias Mitigation using Masked Language Modeling. (arXiv:2201.08643v1 [cs.CL])

It is well known that textual data on the internet and other digital
platforms contain significant levels of bias and stereotypes. Although many
such texts contain stereotypes and biases that inherently exist in natural
language for reasons that are not necessarily malicious, there are crucial
reasons to mitigate these biases. For one, these texts are being used as
training corpus to train language models for salient applications like
cv-screening, search engines, and chatbots; such applications are turning out
to produce …

arxiv bias language modeling style transfer text text style transfer