A Benchmark of Text Classification in PyTorch
A Benchmark of Text Classification in PyTorch
We are trying to build a Benchmark for Text Classification including
Many Text Classification DataSet, including Sentiment/Topic Classfication, popular language(e.g. English and Chinese). Meanwhile, a basic word embedding is provided.
Implment many popular and state-of-art Models, especially in deep neural network.
We have done some dataset and models
You should have install these librarys
python3 torch torchtext (optional)
Dataset will be automatically configured in current path, or download manually your data in Dataset, step-by step.
including
Glove embeding Sentiment classfication dataset IMDB
Run in default setting
python main.py
CNN
python main.py --model cnn
LSTM
python main.py --model lstm
The core of this repository is models and dataset.
dataloader/
: loading all dataset such as IMDB
, SST
models/
: creating all models such as FastText
, LSTM
,CNN
,Capsule
,QuantumCNN
,Multi-Head Attention
opts.py
: Parameter and config info.
utils.py
: tools.
dataHelper
: data helper
Welcome your issues and contribution!!!