Skip to content

TensorFlow-based implementation of Stanford's Attentive Reader for the CNN/DailyMail datatset

Notifications You must be signed in to change notification settings

tspeterkim/attentive-reader

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

14 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Attentive Reader

This is a TensorFlow implementation of the modified Attentive Reader in the paper A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task by Danqi Chen, Jason Bolton, and Christopher Manning.

The data preprocessing step is identical to the one presented in the official Theano/Lasagne implementation here. The good stuff comes after, when the TensorFlow computation graph is built.

Dependencies

  • Python 2.7
  • Tensorflow >= 1.1

Usage

Datasets

To download the CNN/DailyMail datasets, and the GloVe embeddings, run the following script:

./get_dataset.sh

Training

python main.py

About

TensorFlow-based implementation of Stanford's Attentive Reader for the CNN/DailyMail datatset

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published