Text Classification

• Dataset: yahoo_answers_csv (yahoo)
• Model: CNN/LSTM/GRU.
• Pytorch: 1.0.1
• Python: 3.6
• torchtext: 0.3.1.
• Support pretrained word embedding.(word2vec)

torchtext

• This package can provide an elegant way to build vocabulary(torchtext).

TEXT.build_vocab(dataset, vectors)

Training

• The following command starts training.

python main.py

Refs

• Kim, Y. J. E. A. (2014). "Convolutional Neural Networks for Sentence Classification."
• cnn-text-classification-pytorch
• Understanding LSTM Networks