insuranceqa-pytorch

Implementation of LSTM based Deep Learning Models for Non-Factoid Answer Selection by Ming et al.

TODO:

1. Implement attention.
2. 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:

1. Clone the dataset in the directory where model.py is present.
2. Run model.py