What's changed: Added per-section figures (cert-figure-retrofit). Added a speech section (s3) to AI-103 Chapter 5 (the official text-analysis domain’s "speech" sub-area = STT/TTS, speech as agent modality, custom speech / custom neural voice, multimodal reasoning from audio, speech translation). Existing s1 (Azure AI Language) and s2 (translation/custom language models) preserved non-destructively
5.1Text Analysis with Azure AI Language
Understand implementing text information extraction by calling Azure AI Language’s prebuilt features—sentiment analysis, key phrase extraction, entity recognition (NER), language detection, and PII detection—from a developer’s view.
For text apps, call prebuilt Azure AI Language as APIs. Key features: sentiment analysis (positive/negative/neutral with scores), key phrase extraction (important phrases), entity recognition (NER) (extract people, places, dates), language detection (identify input language), and PII detection (detect/mask personal info). Developers authenticate with managed identity and send text via SDK/REST to get structured results.
| Goal | Feature |
|---|---|
| Judge positive/negative | Sentiment analysis |
| Pull out key phrases | Key phrase extraction |
| Extract people/places/dates | Entity recognition (NER) |
| Identify the input language | Language detection |
| Detect/mask personal info | PII detection |
Common: (1) "positive/negative" = sentiment analysis; "important phrases" = key phrase extraction; "people/places/dates" = entity recognition (NER); "identify input language" = language detection; "mask personal info" = PII detection. (2) Generic text tasks = call prebuilt Azure AI Language APIs (managed-identity auth).
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.