StudyToCert

All certifications / Azure AI Fundamentals / Lessons

Microsoft Certified: Azure AI Fundamentals AI-900 · Domain 4: Natural language processing workloads on Azure

Tokenization, embeddings and semantic similarity: how text becomes numbers

▶ Watch the overview video

Last reviewed September 25, 2026 · Leer en español

Machine learning models work with numbers, not words. Every NLP system, from a sentiment classifier to a large language model, must first turn text into numeric form. AI-900 expects you to understand the main steps conceptually: tokenization, frequency-based representations and embeddings.

Free account

Keep reading for free

Create a free StudyToCert account to read the rest of this lesson: 5 more sections, 4 key terms, a real-world example, an exam tip and self-check questions. Every lesson, lab and practice test is free with an account.

Sign up free Log in

Study Azure AI Fundamentals for free
A week-by-week plan with every lesson, quizzes, checkpoint tests, a practice exam and hands-on labs.
Open the Azure AI Fundamentals study plan