Tensorflow implementation of Google DeepMind's Teaching Machines to Read and Comprehend. This implementation contains:

1. Deep LSTM Reader
   • with skip connections from the inputs to all hidden layers
   • with peephole weights that provide precise timing
2. Attentive Reader (in progress)
   • with Bidirectional LSTMs with peephole weights
3. Impatient Reader (in progress)
   • with Bidirectional LSTMs with peephole weights
   • with recurrent accumulation of information from the document while reading the query

• Python 2.7 or Python 3.3+
• Tensorflow
• NLTK
• Gensim

First, you need to download DeepMind Q&A Dataset from here, save cnn.tgz and dailymail.tgz into the repo, and run:

$ ./unzip.sh cnn.tgz dailymail.tgz

Then run the pre-processing code with:

$ python data_utils.py data cnn

To train a model with cnn dataset:

$ python main.py --dataset cnn

To test an existing model:

$ python main.py --dataset cnn --forward_only True

(in progress)

in progres, should be like:

Taehoon Kim / @carpedm20