Tolga Bolukbasi, Kai-Wei Chang, James Zou, Venkatesh Saligrama, Adam Kalai
TL;DR通过研究 word embedding 中的性别特征,开发了一种有效算法,减少性别刻板印象又能保留嵌入的有用几何特性。
Abstract
machine learning algorithms are optimized to model statistical properties of
the training data. If the input data reflects stereotypes and biases of the
broader society, then the output of the learning algorithm also captures these
stereotypes. In this paper, we initiate the study of <