Interpretable Debiasing of Vectorized Language Representations with Iterative Orthogonalization

Interpretable Debiasing of Vectorized Language Representations with Iterative Orthogonalization
复制标题

通过迭代正交化矢量化语言表示的可解释去偏

DOI:
--
复制
发表时间:
2023
期刊:
International Conference on Learning Representations
影响因子:
--
通讯作者:
Jeff Phillips
Jeff Phillips
中科院分区:
--
文献类型:
--
作者:
Prince Osei Aboagye;Yan Zheng;Jack Shunn;Chin-Chia Michael Yeh;Junpeng Wang;Zhongfang Zhuang;Huiyuan Chen;Liang Wang;Wei Zhang;Jeff Phillips

文献摘要

相似文献