most citedReducing Gender Bias in Word-Level Language Models with a Gender-Equalizing Loss Function

8 citations · 8 across the 1 of their papers we have counts for

collaborators

1 paper

cs.CL2019★ 8 cited

Reducing Gender Bias in Word-Level Language Models with a Gender-Equalizing Loss Function

Yusu Qian, Urwa Muaz, Ben Zhang +1

Gender bias exists in natural language datasets which neural language models tend to learn, resulting in biased text generation. In this research, we propose a debiasing approach b…