PractitionerML202

Natural Language Processing with Python

Understand how text becomes data: tokenisation, representations, embeddings, and evaluation. Built around the judgment skills practitioners need to direct AI tools confidently and catch silent NLP failures.

Lessons are AI-assisted and human-reviewed. Learn more.

Syllabus

Text as Data

The NLP Workflow: What "Correct" Looks LikeFree preview

Tokenisation and Normalisation: What AI Tools Change Without Telling You

Text Representations: From Counts to Embeddings

Classical NLP as a Baseline

TF-IDF and Document Similarity: The Baseline You Must Know

Text Classification Pipelines: Building Them Right (and Catching What AI Gets Wrong)

LLM-Native NLP

LLM-Assisted NLP: When to Prompt, When to Train

Embeddings and Semantic Understanding

Word and Sentence Embeddings: What They Encode, What They Miss

Semantic Similarity and Vector Search: The Foundation of RAG

Embedding Failure Modes: What AI Gets Wrong and How to Catch It

Evaluation and Production

Evaluating NLP Models: Metrics Beyond Accuracy

End-to-End NLP Pipelines: From Raw Text to Production