Code for "Semantically Equivalent Adversarial Rules for Debugging NLP Models"
Switch branches/tags
Nothing to show
Clone or download
Latest commit 7bf1020 Oct 16, 2018
Permalink
Failed to load latest commit information.
sears changed default path May 17, 2018
translation_models minor May 17, 2018
Computing SEARs for sentiment analysis.ipynb readme, minor path change May 17, 2018
LICENSE license Oct 16, 2018
README.md readme, minor path change May 17, 2018
polarity.pkl adding stuff May 17, 2018

README.md

sears

Code for Semantically Equivalent Adversarial Rules for Debugging NLP Models

Installation

Run the following:

git clone git@github.com:marcotcr/sears.git
cd sears
virtualenv -p python3 ENV
source ENV/bin/activate
pip install editdistance keras numpy jupyter tensorflow-gpu==1.3.0 torchtext==0.1.1 spacy==1.9.0
pip install http://download.pytorch.org/whl/cu80/torch-0.2.0.post3-cp35-cp35m-manylinux1_x86_64.whl
python -m ipykernel install --user --name=sears
python -m spacy download en
git clone https://github.com/marcotcr/OpenNMT-py
cd OpenNMT-py/
python setup.py install
cd ..

Download and unpack the translation models into the translation_models folder.

Run jupyter notebook, change kernel to sears, and run the notebook :)