MAI4CAREU - Natural Language Processing - Text Classification

The University of Cyprus's course on Natural Language Processing is part of the Master programmes in Artificial Intelligence 4 Careers in Europe (MAI4CAREU). One of Master's programme's courses is split up into several lectures and is taught by Demetris Paschalides from the Department of Computer Science, whose research interest is focused on the use of Natural Language Processing (NLP) and Machine Learning (ML) to address social and ethical challenges.

Learning outcomes

This lecture looks at:

• Types of Classification: 

  • Rule-based Classification 

  • Supervised Classification

• Introduction to Text Vectorization - Input to ML models. 

  • Example of vectorization: Bag-of-Words 

• Probabilistic Classification 

  • Example of Naive Bayes 

  • Naive Bayes as a Language Model Classification Evaluation.

Course outline

The Natural Language Processing course is divided into 7 subsections: 

1. Text Pre-processing 

2. Language Modeling 

3. Text Classification 

4. Word Vector Representation 

5. Distributed Contextual Embeddings 

6. Application of NLP in: 

   1. Hate-speech Identification 

   2. Fake News Detection 

   3. Political Polarization 

7. Introduction to Large Language Models