Skip to content

Natural Language Processing: A Notebook-Based Introduction

Overview

mlciv/nlp-notebooks

Natural Language Processing: A Notebook-Based Introduction

mlciv/nlp-notebooks

Home
The Book
The Book
- Preface
- Roadmap
- License
Chapters
Chapters
- I — Language Model Foundations
  I — Language Model Foundations
  - Overview Overview
    Table of contents
    
    Chapters in this part
    
    What you'll be able to do
  - 1 · Tokenization & Vocabulary
  - 1 · Setup Tutorial
  - 1 · AI Usage Example
- II — Machine Learning Foundation and NLP Tasks
  II — Machine Learning Foundation and NLP Tasks
  - Overview
  - 2 · Text Classification
- III — Representations & Sequences
  III — Representations & Sequences
  - Overview
  - 3 · Embeddings & Sequence Models
- IV — Transformers & LLMs
  IV — Transformers & LLMs
- V — LLM Alignment and Agentic AI
  V — LLM Alignment and Agentic AI
Course
Course

I — Language Model Foundations¶

This part establishes the groundwork for everything that follows: how raw text becomes something a model can compute on, and the first statistical language models.

Chapters in this part¶

Chapter 1: Tokenization & Vocabulary — How text is split into tokens, how subword vocabularies (e.g. BPE) are built, out-of-vocabulary handling, and a first look at n-gram language modeling. Supporting notebooks: Setup Tutorial · AI Usage Example.

What you'll be able to do¶

Explain how modern tokenizers segment text and why subword units matter.
Inspect and analyze a real tokenizer's vocabulary.
Build an n-gram language model and use it to score and generate text.