BriefGPT.xyz
Nov, 2019
一种因果推断方法用于减少词嵌入关系中的性别偏见
A Causal Inference Method for Reducing Gender Bias in Word Embedding Relations
HTML
PDF
Zekun Yang, Juan Feng
TL;DR
本研究提出了一种基于统计依存关系的方法来消除词向量关系中的性别偏差，有效避免了词向量关系中存在的性别偏见问题，并在多个联想任务中实现了最先进的结果。
Abstract
word embedding
has become essential for natural language processing as it boosts empirical performances of various tasks. However, recent research discovers that
gender bias
is incorporated in
→