You have a text-based chatbot.
You need to enable content moderation by using the Text Moderation API of Content Moderator.
Which two service responses should you use? Each correct answer presents part of the solution.
NOTE: Each correct selection is worth one point.
To enable content moderation using the Text Moderation API of Content Moderator for a text-based chatbot, the correct service responses to use are personal data and text classification. Personal data response helps identify and potentially mask sensitive information like names, addresses, phone numbers, etc., thus protecting user privacy. Text classification response allows the API to analyze the text for potentially harmful or inappropriate content, such as hate speech, bullying, or threats, ensuring a safer and more positive interaction environment. These functionalities are essential for effective content moderation in text-based applications.
AC is the answer. https://learn.microsoft.com/en-us/azure/cognitive-services/content-moderator/text-moderation-api Use Content Moderator's text moderation models to analyze text content, such as chat rooms, discussion boards, chatbots, e-commerce catalogs, and documents. The service response includes the following information: - Profanity: term-based matching with built-in list of profane terms in various languages - Classification: machine-assisted classification into three categories - Personal data - Auto-corrected text - Original text - Language
Gotten this in Jul 2023 exam.
Correct! While A, C belong to Text Moderation https://learn.microsoft.com/en-us/azure/ai-services/content-moderator/text-moderation-api, B, E belong to Vision AI https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/concept-detecting-adult-content#content-flag-definitions
Answer is correct. The reference URL: https://learn.microsoft.com/en-us/azure/cognitive-services/content-moderator/api-reference
Based on the information from the official Azure Cognitive Services documentation, it seems that the Text Moderation API indeed returns profanity terms and personal data (A), which can be used for content moderation. It also performs text classification (C), which can be used to categorize and filter content. So, the correct answers according to the official Azure documentation are A. personal data and C. text classification.
B. the adult classification score E. the racy classification score To enable content moderation in a text-based chatbot using the Text Moderation API of Content Moderator, you should use the adult classification score (B) and the racy classification score (E). These scores will help you determine if the content is adult or racy in nature, enabling you to take appropriate action for moderation purposes.
answer is correct: https://westus.dev.cognitive.microsoft.com/docs/services/57cf753a3f9b070c105bd2c1/operations/57cf753a3f9b070868a1f66f request parameters: PII and classify
answer is correct: https://westus.dev.cognitive.microsoft.com/docs/services/57cf753a3f9b070c105bd2c1/operations/57cf753a3f9b070868a1f66f request parameters: PII and classify
C. Text classification A. Personal data Here's why these two are important: Text classification: This functionality allows the API to analyze the text for potentially harmful content like hate speech, bullying, threats, etc. This is crucial for ensuring a safe and positive environment in your chatbot. Personal data: This helps identify and potentially mask sensitive information like names, addresses, phone numbers, etc., which users might accidentally or intentionally reveal during conversations. This protects user privacy. Let's break down the other options: B. The adult classification score: This functionality is not available in the Text Moderation API. It's likely part of the Content Moderator's Image Moderation API for identifying inappropriate visuals. D. Optical character recognition (OCR): This is not relevant for text-based chatbots as OCR deals with converting images containing text into machine-readable format. E. The racy classification score: Similar to adult classification score, this functionality is likely intended for image moderation and not directly applicable to text analysis.
AC is answer.
Image Moderation API Scan images and detect potential adult and racy content by using tags, confidence scores, and other extracted information. Text Moderation API Scan text content. Profanity terms and personal data are returned.
Based on the official documentation correct answer seems to be AC https://learn.microsoft.com/en-us/azure/cognitive-services/content-moderator/text-moderation-api
The appropriate service responses for content moderation using the Text Moderation API of Content Moderator are: A. Personal Data and C. Text Classification. These features help identify sensitive information and categorize text content based on its potential appropriateness, including detecting profanity, personal data, and classifying text into categories related to potentially undesired content​ PLEASE DO NOT SELECT A,C!!!
AC is the answer.