BriefGPT.xyz
Sep, 2021
评估词向量性别偏差度量的可靠性
Assessing the Reliability of Word Embedding Gender Bias Measures
HTML
PDF
Yupei Du, Qixiang Fang, Dong Nguyen
TL;DR
本研究评估了三种类型的词嵌入性别偏见度量的可信度，包括测试再测试可靠性、评分者一致性和内部一致性，并考察了不同随机种子、评分规则和单词选择等因素对可信度的影响，结果有助于更好地设计性别偏差度量，同时也建议研究者对这些度量的应用更加持批判态度。
Abstract
Various measures have been proposed to quantify human-like
social biases
in
word embeddings
. However, bias scores based on these measures can suffer from measurement error. One indication of
→