This module sets the scene and explains the fundamental concepts of both linguistics and NLP. You will understand the importance of NLP in modern technology and everyday life. Furthermore, this section introduces major platforms and packages such as NLTK, spaCy, and Hugging Face which will be used later in the hands-on activities in the upcoming modules.
By the end of this module, you will acquire essential skills in text pre-processing and feature engineering. You will learn key techniques such as tokenization, lemmatization (symbolic/deterministic NLP), Bag-of-Words, TF-IDF vectorization and Ngrams (statistical NLP), enabling you to prepare and represent text data effectively. Through a real-world use case, you'll also gain experience in applying these techniques for practical tasks like Author Attribution.
This module contains an exercise about heuristic authorship attribution.
In this module you’ll move from foundational knowledge in traditional, probabilistic models towards deep learning. You'll gain insights into classic models like Naive Bayes classification and Hidden Markov Models (HMMs).
This module contains an exercise about hate speech classification with Naive Bayes.
By the end of this module, you'll know the basics of advanced NLP technologies like the attention mechanism and transformers. We’ll look at how BERT can be fine tuned and used for specific tasks like text classification. You'll also understand the architecture, significance, and real-world applications of large language models (LLMs).
This module contains an exercise about classifying movie reviews with Transformers.
In the final module, you'll explore various real-world applications of NLP across sectors like healthcare, finance, and customer service. You'll also gain awareness of the ethical considerations when applying NLP. This module serves as a capstone, integrating all the skills and knowledge gained throughout the course and pointing you toward further learning opportunities. A last use case teaches you how to leverage LLMs and Retrieval-Augmented Generation (RAG) to build a chat bot that accesses a custom knowledge base.
This module contains an exercise about LLMs and Retrieval Augmented Generation (RAG).