BriefGPT.xyz
Sep, 2018
抽取式对抗网络：基于高召回率的社交媒体帖子个人攻击识别解释
Extractive Adversarial Networks: High-Recall Explanations for Identifying Personal Attacks in Social Media Posts
HTML
PDF
Samuel Carton, Qiaozhu Mei, Paul Resnick
TL;DR
通过在现有的精细硬性注意力解释结构上添加对抗性层，可以提高模型对神经文本分类器决策进行高召回解释的能力，并更好地检测社交媒体评论中的个人攻击。
Abstract
We introduce an
adversarial method
for producing high-recall explanations of
neural text classifier
decisions. Building on an existing architecture for
→