A complete, hands-on NLP series: from text preprocessing and word embeddings to text classification, attention, large language models, chatbots, and deployment.
Natural Language Processing, or NLP, is how computers make sense of human language: the messy, ambiguous, context-dependent way people actually write and speak. It is the field behind search engines, spam filters, translation, voice assistants, and the large language models that power tools like ChatGPT. This series takes you the whole way, from a raw string of text up to modern Transformer-based language models, with working Python at every step. It is written to be read in order, and each chapter leads into the next.
The aim is to give you both the intuition and the practice. We start with classical methods, because they are simpler and still widely used, then build up to deep learning and Transformers, so you understand not just how to call a library but why it works.
The chapters are grouped into five parts that move from fundamentals to real applications:
The best place to begin is the introduction to natural language processing.
By the end of the series you will understand the standard NLP pipeline, be able to turn text into numerical features, train and evaluate models for real tasks like classification and entity extraction, understand how attention and Transformers actually work, and build and deploy a working NLP application. You will also be ready for applied work on top of large language models, such as building retrieval-augmented systems.
The series assumes you can read basic Python; everything specific to NLP is explained as it comes up. If you want to brush up first, the Python Programming series is a good start, and the Machine Learning series covers the modelling ideas this builds on. Because modern NLP runs on the same architecture as deep learning generally, the Neural Networks and Deep Learning series is a natural companion, especially its chapter on Transformers.
Sign in to join the discussion and post comments.
Sign in