English and German
Extract the datasets into two folders: english_dataset and german_dataset. Code is run for english dataset for all three tasks.
Among statistical machine learning methods, we have basic Naive-Bayes, SVM and Random Forest algorithms. Advanced models are yet to be included
- Run the preprocessing.py file first to create pickle files required by the statistical models
- Run naive-bayes.py/svm.py/rf.py
- Run the dnn-preprocess.py file first to create pickle files required by the CNN model. Pickle files are created inside a folder called pickle_files
- Run cnn.py to run the CNN model