This repository contains a tool which allows to train a text formality classifier.
For training the classirier the GYAFC parallel corpus is used:
Please follow the instructions to get the corpus.
Clone the repo as:
git clone https://github.com/hbeybutyan/formality_analyzer.git
cd formality_analyzer
Get the GYAFC corpus and extract it:
In the script update the GYAFC_PATH, set it to the dir there you just extracted the GYAFC corpus.
Run script as:
python3 formality_analyzer.py