indobertshare

This repo contains code for my undergraduate thesis: "The Development of Indonesian Paraphrase Dataset for Automatic Paraphrase Generation System"

How To

Create and activate the environment, then install all requirements

virtualenv -p python3.8 venv
source venv/bin/activate
pip install -r requirements.txt

Download liputan6 dataset, then extract

tar -xvf liputan6_data.tar.gz