This is the GUI for out Fact detector. We trained a CNN model with a stacked Highway gate on news articles relating to wikipedia changes. The focus was on changes that were clear changes, e.g. athletes switching teams. The sentences in the articles that contained the fact were labelled using TF-IDF. This model also makes use of Bert embeddings for enhanced results.
Open the terminal and navigate to the folder where you want to put this project.
Clone the GitHub repository
git clone https://github.com/austrian-code-wizard/wikipedia-to-news-gui
Navigate into the directory
cd wikipedia-to-news-gui
Install the virtualenv tool for python
python3 -m pip install virtualenv
Create a new virtual environment
python3 -m virtualenv venv
Activate the virtual environment
. venv/bin/activate
Install dependencies
pip install -r requirements.txt
Run the app
python app.py
Now, open your browser and navigate to the site http://127.0.0.1:5000/