Implementation of LSTM based Deep Learning Models for Non-Factoid Answer Selection by Ming et al.
TODO:
- Implement attention.
- Use GESD similarity instead of cosine.
I referred https://github.com/codekansas/keras-language-modeling and https://github.com/white127/insuranceQA-cnn-lstm for porting the implementation.
Link to dataset: https://github.com/codekansas/insurance_qa_python
To run:
- Clone the dataset in the directory where model.py is present.
- Run model.py