Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
yh 0a33a32081 | 5 years ago | |
---|---|---|
.. | ||
data | 5 years ago | |
model | 5 years ago | |
test | 5 years ago | |
utils | 5 years ago | |
README.md | 5 years ago | |
train_HAN.py | 5 years ago | |
train_awdlstm.py | 5 years ago | |
train_bert.py | 5 years ago | |
train_char_cnn.py | 5 years ago | |
train_dpcnn.py | 5 years ago | |
train_lstm.py | 5 years ago | |
train_lstm_att.py | 5 years ago |
这里使用fastNLP复现以下模型:
char_cnn :论文链接Character-level Convolutional Networks for Text Classification
dpcnn:论文链接Deep Pyramid Convolutional Neural Networks for TextCategorization
HAN:论文链接Hierarchical Attention Networks for Document Classification
LSTM+self_attention:论文链接A Structured Self-attentive Sentence Embedding
AWD-LSTM:论文链接Regularizing and Optimizing LSTM Language Models
使用fastNLP复现的结果vs论文汇报结果(/前为fastNLP实现,后面为论文报道,-表示论文没有在该数据集上列出结果)
model name | yelp_p | yelp_f | sst-2 | IMDB |
---|---|---|---|---|
char_cnn | 93.80/95.12 | - | - | - |
dpcnn | 95.50/97.36 | - | - | - |
HAN | - | - | - | - |
LSTM | 95.74/- | 64.16/- | - | 88.52/- |
AWD-LSTM | 95.96/- | 64.74/- | - | 88.91/- |
LSTM+self_attention | 96.34/- | 65.78/- | - | 89.53/- |
一款轻量级的自然语言处理(NLP)工具包,目标是减少用户项目中的工程型代码,例如数据处理循环、训练循环、多卡运行等
Python Jupyter Notebook Text CSV Markdown