For the Misgendered Chinese in Gender Bias Research: Multi-Task Learning with Knowledge Distillation for Pinyin Name-Gender Prediction

arXiv:2405.06221v1 Announce Type: new
Abstract: Achieving gender equality is a pivotal factor in realizing the UN's Global Goals for Sustainable Development. Gender bias studies work towards this and rely on name-based gender inference tools to assign individual gender labels when gender information is unavailable. However, these tools often inaccurately predict gender for Chinese Pinyin names, leading to potential bias in such studies. With the growing participation of Chinese in international activities, this situation is becoming more severe. Specifically, current tools …

abstract arxiv bias chinese cs.cl cs.cy development distillation equality gender gender bias global inference information knowledge labels multi-task learning pivotal prediction research studies sustainable sustainable development tools type work