In this exercise the main goal is to build 2 Hatespeech classification models
-
A keyword based model classifier
-
A Language Model (LM) based model classifier
This exercise is designed to evaluate your abilities to
- understand an ML problem, propose and implement a solution
- preprocess text data
- implement simple ML models
- evaluate the performance of ML models
- compare the performance of different ML models
- use good code development practises
- use the typical tools of an NLP researcher/engineer....