The project consists of 2 parts: First, we extract the data from the Wikipedia dump files and second, we implement various text classification models like RNN, RCNN, Self-Attention and BERT. This last model is the only one which has been implemented using Google colab (.ipynb file).
Text Classification is one of the basic and most important task of Natural Language Processing. In this repository, we focus on one such text classification task, more in detail in the problem of: Detection of biased language.