Learning Recurrent Span Representations for Extractive Question Answering

https://arxiv.org/abs/1611.01436

Initial setup

$ python setup.py

This will download GloVe word embeddings and tokenize raw training / development data.
(download will be skipped if zipped GloVe file is manually placed in data directory).

Training

$ python train_main.py

Making predictions

$ python predict_main.py

---

Tested in the following environment:

• Ubuntu 16.04
• Python 2.7.13
• NVIDIA CUDA 7.5 and cuDNN 5.1
• Pytorch
• Oracle JDK 8