ashoknp-git/cnn-text-classification-pytorch

CNNs for Text Classification in PyTorch

CNNs for Text Classification in PyTorch

A minimal PyTorch implementation of Convolutional Neural Networks (CNNs) for text classification.

Supported features:

• Mini-batch training with CUDA
• Lookup, CNNs, RNNs and/or self-attentive encoding in the embedding layer

Usage

Training data should be formatted as below:

sentence \t label
sentence \t label
...

To prepare data:

python3 prepare.py training_data

To train:

python3 train.py model char_to_idx word_to_idx tag_to_idx training_data.csv (validation_data) num_epoch

To predict:

python3 predict.py model.epochN char_to_idx word_to_idx tag_to_idx test_data

To evaluate:

python3 evaluate.py model.epochN char_to_idx word_to_idx tag_to_idx test_data

References

Yoon Kim. 2014. Convolutional Neural Networks for Sentence Classification. arXiv:1408.5882.

Yunlun Yang, Yunhai Tong, Shulei Ma, Zhi-Hong Deng. 2016. A Position Encoding Convolutional Neural Network Based on Dependency Tree for Relation Classification. In EMNLP.

Zenan Zhai, Dat Quoc Nguyen, Karin Verspoor. 2018. Comparing CNN and LSTM character-level embeddings in BiLSTM-CRF models for chemical and disease named entity recognition. In Proceedings of the 9th International Workshop on Health Text Mining and Information Analysis (LOUHI).

Xiang Zhang, Junbo Zhao, Yann LeCun. 2015. Character-level Convolutional Networks for Text Classification. arXiv:1509.01626.