文章目录
- CNN系列
- Effective Use of Word Order for Text Categorization with Convolutional Neural Networks
- A Convolutional Neural Network for Modelling Sentences
- Convolutional Neural Networks for Sentence Classification
- Deep Pyramid Convolutional Neural Networks for Text Categorization
- Super Characters: A Conversion from Sentiment Classification to Image Classification
- LSTM系列
- Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification
- Hierarchical Attention Networks for Document Classification
- Pre-train
- 其他
这篇博客只是个索引, 具体的阅读笔记请点击每篇论文的链接.
CNN系列
Effective Use of Word Order for Text Categorization with Convolutional Neural Networks
A Convolutional Neural Network for Modelling Sentences
Convolutional Neural Networks for Sentence Classification
Deep Pyramid Convolutional Neural Networks for Text Categorization
Super Characters: A Conversion from Sentiment Classification to Image Classification
主要思想：把文字转化成图，然后用图片进行训练。
<center>
</center> LSTM系列
Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification
Hierarchical Attention Networks for Document Classification
Pre-train
Fine-tuned Language Models(FitLaM)
算是ULMFiT的前身, 基本一样.
京公网安备 11010502036488号