这个Repo主要记录自己学习NLP一些基础任务的历程以及代码实现,主要包括文本分类、实体识别以及Aspect情感分析,会随着学习的进程逐步更新代码。
该部分主要基于两个数据集进行实验,一个是IMDB评论数据集,一个是Yelps评论数据集。这两个都是Kaggle上别人选取的部分数据集,也可以自己准备。
FastText
论文:Bag of Tricks for Efficient Text Classification
TextCNN
论文:Convolutional Neural Networks for Sentence Classification
CharCNN
论文:Character-level Convolutional Networks for Text Classification
BiLSTM
BiLSTM+Attention
论文:Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Claasification
RCNN
论文:Recurrent Convolutional Neural Networks for Text Classification
Adversarial LSTM
论文:Adversarial Training Methods for Semi-Supervised Text Classification
HAN
论文:Multilingual Hierarchical Attention Networks for Document Classification
DPCNN
论文:Deep Pyramid Convolution Neurail Networks for Text Categorization