LiDA: Language-independent Data Augmentation for Text Classification

This repository contains the source code and the datasets for LiDA.

Usage

Training Baseline models

LSTM

python main.py

SBERT

cd sbert
python main.py

Run the experiment

LSTM

Open the experiment.py file and adjust the parameters before running it.

python experiment.py

SBERT

Go to sbert folder, open the experiment.py file and adjust the parameters before running it.

python experiment.py