This is a ๐ฅ PyTorch ๐ฅ implementation of the seminal BiDAF Paper from Allen AI(https://arxiv.org/pdf/1611.01603.pdf)
My modifications include ๐ :
- QA on a token level instead of a character level ( I use Spacy 2.1.9 to create the dataset from SQUAD )
- Swapping out GloVe for Elmo for improved performance
I have uploaded a sample dataset from the SQUAD Dataset. Download the complete dataset at SQUAD QA Dataset
I have also implemented a Streamlit App to interact with the model!
pip install -r requirements.txt
python train.py
streamlit run app.py
โ๏ธ Pull requests are welcome for any improvements/features โ๏ธ