https://github.com/kihyunwon/dynamic-coattention-network

Tensorflow implementation of Dynamic Coattention Networks for Question Answering.
https://github.com/kihyunwon/dynamic-coattention-network

Last synced: 8 days ago
JSON representation

Tensorflow implementation of Dynamic Coattention Networks for Question Answering.

• Host: GitHub
• URL: https://github.com/kihyunwon/dynamic-coattention-network
• Owner: kihyunwon
• License: mit
• Created: 2016-11-30T09:47:52.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2016-12-04T03:34:02.000Z (over 7 years ago)
• Last Synced: 2024-05-22T07:52:48.949Z (about 1 month ago)
• Language: Python
• Homepage:
• Size: 19.5 KB
• Stars: 101
• Watchers: 6
• Forks: 45
• Open Issues: 8
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Lists

• awesome-deeplearning-resources - Tensorflow implementation of Dynamic Coattention Networks for Question Answering.

README

        
Dynamic Coattention Networks For Question Answering

===========================================================

Tensorflow implementaion of [Dynamic Coattention Networks](https://arxiv.org/abs/1611.01604).

This repo contains work on progress.

Requirements

--------------

- Python 3.5.2

- TensorFlow r0.11

- spaCy 1.2.0

Data

-----

Retrieve json training files from [SQuAD](https://rajpurkar.github.io/SQuAD-explorer/).

```dataset.py``` contains code to create a dataset and vocab for training network.

Training the network

-----------------------

In order to train the network, execute

```

python main.py --mode train

```

Credit

-------

Modified codes are originally from [textsum](https://github.com/tensorflow/models/tree/master/textsum).