Tensorflow implementation of Semi-supervised Sequence Learning(https://arxiv.org/abs/1511.01432).

Auto-encoder or language model is used as a pre-trained model to initialize LSTM text classification model.

• SA-LSTM: Use auto-encoder as a pre-trained model.
• LM-LSTM: Use language model as a pre-trained model.

• Python 3
• Tensorflow
• pip install -r requirements.txt

DBpedia dataset is used for pre-training and training.

$ python pre_train.py --model="<MODEL>"

(<Model>: auto_encoder | language_model)

$ python train.py --pre_trained="<MODEL>"

(<Model>: none | auto_encoder | language_model)

• Orange lines: LSTM
• Blue lines: SA-LSTM
• Red lines: LM-LSTM