Investigating Societal Biases in a Poetry Composition System

Proceedings of the Second Workshop on Gender Bias in Natural Language Processing(2020)

引用 41|浏览349
暂无评分
摘要
There is a growing collection of work analyzing and mitigating societal biases in language understanding, generation, and retrieval tasks, though examining biases in creative tasks remains underexplored. Creative language applications are meant for direct interaction with users, so it is important to quantify and mitigate societal biases in these applications. We introduce a novel study on a pipeline to mitigate societal biases when retrieving next verse suggestions in a poetry composition system. Our results suggest that data augmentation through sentiment style transfer has potential for mitigating societal biases.
更多
查看译文
关键词
poetry,societal biases,composition
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络