Chapter 4 · Natural Language Processing·v2.1.0·Updated 6/3/2026·~12 min
What's changed: Deepened AI-900 Chapter 4 to the AZ-900 baseline (how NLP works = tokens/embeddings/Transformer, question answering, custom features CLU/custom QnA/Custom Speech/Translator, FAQ)
4.2Azure Language and Speech Services
Key points
Understand Azure’s NLP services—Azure AI Language, Azure AI Speech, and Azure AI Translator—and when to use each.
Azure offers NLP services you can use without building your own model. The selection axis is "text understanding," "spoken audio (speech)," or "translation between languages"—plus "conversation (chatbots)."
4.2.1Key services
- Azure AI Language: text understanding—sentiment, entity recognition, key phrases, language detection, summarization, PII detection, CLU, question answering.
- Azure AI Speech: speech ⇄ text (speech-to-text, text-to-speech) and speech translation.
- Azure AI Translator: text translation between languages.
- Azure AI Bot Service: build chatbots by combining CLU and question answering.
| Goal | Service |
|---|---|
| Sentiment/entities/summary of text | Azure AI Language |
| Transcribe / synthesize speech | Azure AI Speech |
| Translate text across languages | Azure AI Translator |
| Interpret intent (bots) | Azure AI Language (CLU) + Bot Service |
Continue reading — free sign-up
You're reading the free preview. Sign up free to read this section in full, plus every chapter (including 4+) and all questions.