hummingbird
/
fastNLP
Not watched
2
0
Fork 0
Code
Releases 13 Wiki Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain
You can not select more than 25 topics Topics must start with a chinese character,a letter or number, can include dashes ('-') and can be up to 35 characters long.
1127 Commits
3 Branches
25 MB
0 Download
 
 
 
 
 
Tree: bedb792b3c
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'bedb792b3c'
${ noResults }
fastNLP/reproduction/text_classification
xuyige 570b214dfb 增加fastNLP.embeddings模块并修改对应的现有代码以适配fastNLP.embeddings 5 years ago
..
data [verify] train_char_cnn optimization 5 years ago
model 增加fastNLP.embeddings模块并修改对应的现有代码以适配fastNLP.embeddings 5 years ago
test add TC/MTL16Loader 5 years ago
utils -update DPCNN & train script 5 years ago
README.md update README.md 5 years ago
train_HAN.py 增加fastNLP.embeddings模块并修改对应的现有代码以适配fastNLP.embeddings 5 years ago
train_awdlstm.py 增加fastNLP.embeddings模块并修改对应的现有代码以适配fastNLP.embeddings 5 years ago
train_bert.py add text_classification reproduction dir 5 years ago
train_char_cnn.py 增加fastNLP.embeddings模块并修改对应的现有代码以适配fastNLP.embeddings 5 years ago
train_dpcnn.py 增加fastNLP.embeddings模块并修改对应的现有代码以适配fastNLP.embeddings 5 years ago
train_lstm.py 增加fastNLP.embeddings模块并修改对应的现有代码以适配fastNLP.embeddings 5 years ago
train_lstm_att.py 增加fastNLP.embeddings模块并修改对应的现有代码以适配fastNLP.embeddings 5 years ago

README.md

text_classification任务模型复现

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

数据集及复现结果汇总

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/-
Delete task

Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.

cancel
confirm

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