Chapter 7. Features of Natural Language Processing Workloads on Azure
In this chapter, we’ll look into NLP, a key topic that makes up about 15%–20% of the AI-900 exam. We’ll kick things off with an exploration of core NLP scenarios. Then, we’ll get into Microsoft Azure services for NLP, starting with key phrase extraction and how entity recognition pulls important context from text. From there, we’ll walk through sentiment analysis, an essential tool for reading emotions in written language, and cover the basics of language modeling. You’ll also find an introduction to speech recognition and synthesis. This is where machines learn to understand and produce humanlike speech. Finally, we’ll wrap up with how to use NLP with conversational language understanding (CLU) and conversational AI.
Introduction to NLP
Imagine trying to get your computer to not just read but actually understand what you’re saying—that’s where NLP steps in. NLP is a part of AI that gives machines the power to interpret and generate human language. It’s about taking apart the complexities of text and speech and transforming them into something a computer can work with. This is what fuels everything from the search results you see on Google to chatbots to generative AI apps like ChatGPT that answer questions and those voice-activated assistants that talk back. By bridging the gap between human communication and computer logic, NLP makes technology feel more intuitive—almost like it’s listening.
NLP doesn’t work ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access