DSL

Discrimination of Similar Languages

Environment

pip install -r requirements.txt

Dataset & Preprocessing

Download the dataset from DSLLCC We use DSLCC v4.0

You should change the directory in the file

python preprocessing.py 

Usage

SVM baselines

python -m svm.svm [charngram/2step]

Neural baselines

python -m charcnn.main --save_dir [checkpoints/temp] --model [bow/cnn/multicnn]