Rationale Prediction

Using Gumbel Softmax instead of REINFORCE.

Requirements

1. Pytorch 1.0
2. AllenNLP
3. nltk
4. tqdm

See models/train.py for details of commandline options.

1. Rotten Tomatoes;
2. Congress Dataset (ETH internal only);
3. BeerReview Dataset (TODO).

TODO

Name		Name	Last commit message	Last commit date
Latest commit History 7 Commits
data		data
data_utils		data_utils
models		models
README.md		README.md
elmo_test.py		elmo_test.py
main.py		main.py
param_generator.py		param_generator.py
run.sh		run.sh