You have a blog that allows users to append feedback comments. Some of the feedback comments contain harmful content that includes discriminatory language. You need to create a prototype of a…

Question

Options

• ASign in to Content Safety Studio and select Moderate text content.
• BSign in to Content Safety Studio and select Protected material detection for text.
• CFrom the Azure portal, create an Azure AI Content Safety resource.
• DSign in to Azure AI Foundry and select Safety + security.
• EFrom the Azure portal, create an Azure OpenAI resource.

• A
  82% (27)
• B
  9% (3)
• D
  3% (1)
• E
  6% (2)

Explanation

A: The Azure AI Content Safety Studio is a tool that helps detect harmful content in text, images, and multimodal formats like memes. It uses machine learning models to identify potentially offensive, risky, or undesirable content, offering both pre-defined and customizable moderation categories. This allows for a more tailored approach to content moderation, going beyond basic content safety options. C: Get started with the Content Safety Studio, REST API, or client SDKs to do basic text moderation. The Azure AI Content Safety service provides you with AI algorithms for flagging objectionable content. https://learn.microsoft.com/en-us/azure/ai-services/content-safety/overview https://learn.microsoft.com/en-us/azure/ai-services/content-safety/quickstart-text

No community discussion yet for this question.