论文笔记:《dEFEND: Explainable Fake N

2020-09-26  本文已影响0人  IT_小马哥

摘要

引言

相关工作

问题陈述

模型

新闻内容编码

单词编码

句子编码

用户评论编码

句子和评论的共注意力机制

预测

实验

数据集

实验结果

实验结果

RST: we used the publicly available implementation for paper
[17]: https://github.com/jiyfeng/DPLP
• LIWC: we used the publicly available tool at:
http://liwc.wpengine.com/
• text-CNN: we used the publicly available implementation at:
https://github.com/dennybritz/cnn-text-classification-tf
• HAN: we used the publicly available implentation at:
https://github.com/richliao/textClassifier
• TCNN-URG: we implemented this algorithm based on the
description in the paper [35], and shared the code, named as
tcnn.py, in the above link
• HPA-BLSTM: we used the implementation provided by the
authors of [13]
• CSI: we used the implementation available at:
https://github.com/sungyongs/CSI-Code
• dEFEND:we implemented our algorithm in Python–defend.py
for main algorithm and go_defend.py for data processing–
and shared them in the https://tinyurl.com/ybl6gqrm

问题一

问题二

问题三

新闻句子的可解释性

用户评论

上一篇 下一篇

猜你喜欢

热点阅读