This code is for our proposed model in DL-NLP course.
- Steps to run this model:
- Datasets of MR, SST-2, R8 and 20ng should be put under Data/ and path needs to be updated in config.py file.
- For parameter tuning, use config.py file and change parameters.
- python3 train.py
Baselines:
- TF-IDF with Logistic Regression:TF-IDF + LR
- LSTM with pre-trained GloVe embeddings(d=300) : LSTM - GloVe
- Code for TGCN and VGCN-BERT: adjacency.ipynb + gcn.py + train.py
Dataset Statistics:
Results:
Project Report- Final_Project_Report.pdf