AI-900 practice questions 21–30

1. Question 21 · 236 in bank

   You are authoring a Language Understanding (LUIS) application to support a music festival. You want users to be able to ask questions about scheduled shows, such as: `Which act is playing on the main stage?` The question `Which act is playing on the main stage?` is an example of which type of element?

   • Aan intent
   • Ban utterance
   • Ca domain
   • Dan entity

   Show answer

   Answer: B

   Explanation

   Correct answer. In the context of a Language Understanding (LUIS) application, an utterance refers to a specific user input or query. It represents a single sentence or phrase that users provide to interact with the application. In this case, the utterance "Which act is playing on the main stage?" represents a user's question about the scheduled shows at the music festival. By collecting and annotating a variety of utterances like this, the LUIS application can learn to understand user intents and extract relevant entities from the input. To further clarify the other options: - An intent represents the purpose or goal behind a user's utterance. It captures the user's intention or desired action. - A domain refers to a specific area or topic of knowledge, such as music, sports, or weather. - An entity represents a specific piece of information or data within an utterance. In this case, an entity could be "main stage," which refers to a specific stage at the music festival. Therefore, the correct answer is B. an utterance.

   Source: Adapted from community discussion — rdemontis

   Next question

2. Question 22 · 236 in bank

   You build a QnA Maker bot by using a frequently asked questions (FAQ) page. You need to add professional greetings and other responses to make the bot more user friendly. What should you do?

   • AIncrease the confidence threshold of responses
   • BEnable active learning
   • CCreate multi-turn questions
   • DAdd chit-chat

   Show answer

   Answer: D

   Explanation

   Correct answer. Adding chit-chat functionality to the bot involves including pre-built conversational responses for general small talk or non-FAQ related interactions. Chit-chat responses can enhance the user experience by providing friendly greetings, acknowledgments, and appropriate responses to casual or non-specific queries. Options A and B are not directly related to adding greetings and other user-friendly responses. Option C, creating multi-turn questions, refers to handling conversations with multiple interrelated questions and responses. While it can contribute to a more interactive experience, it does not address the specific requirement of adding professional greetings and other user-friendly responses

   Source: Adapted from community discussion — rdemontis

   Next question

3. Question 23 · 236 in bank

   You need to develop a chatbot for a website. The chatbot must answer users' questions based on the information in the following documents: ✑ A product troubleshooting guide in a Microsoft Word document ✑ A frequently asked questions (FAQ) list on a webpage Which service should you use to process the documents?

   • AAzure Bot Service
   • BLanguage Understanding
   • CText Analytics
   • DQnA Maker

   Show answer

   Answer: D

   Explanation

   The QnA Maker service is being retired on the 31st of March, 2025. A newer version of the question and answering capability is now available as part of Azure Cognitive Service for Language

   Source: Adapted from community discussion — Nabeeel

   References

   • Microsoft Learn

   Next question

4. Question 24 · 236 in bank

   DRAG DROP - Match the types of AI workloads to the appropriate scenarios. To answer, drag the appropriate workload type from the column on the left to its scenario on the right. Each workload type may be used once, more than once, or not at all. NOTE: Each correct selection is worth one point. Select and Place:

   

   This is an interactive task on the real exam — a drag-and-drop, hotspot or ordering question. There is nothing to select here, so the answer is shown below for reference.

   Show the answer figure

   Answer: See figure below

   Explanation

   Reference: https://docs.microsoft.com/en-us/learn/paths/get-started-with-artificial-intelligence-on-azure/

   Source: Adapted from community discussion — idioteque

   References

   • Microsoft Learn
   • Microsoft Learn

   

   Next question

5. Question 25 · 236 in bank

   You are building a Language Understanding model for an e-commerce business. You need to ensure that the model detects when utterances are outside the intended scope of the model. What should you do?

   • ATest the model by using new utterances
   • BAdd utterances to the None intent
   • CCreate a prebuilt task entity
   • DCreate a new model

   Show answer

   Answer: B

   Explanation

   B is correct answer. You cannot only rely on using score thresholds to determine out of domain utterances with an undertrained None intent.

   Source: Adapted from community discussion — kzue

   References

   • Microsoft Learn

   Next question

6. Question 26 · 236 in bank

   Select 2

   Which two scenarios are examples of a natural language processing workload? Each correct answer presents a complete solution. NOTE: Each correct selection is worth one point.

   • Amonitoring the temperature of machinery to turn on a fan when the temperature reaches a specific threshold
   • Ba smart device in the home that responds to questions such as, "What will the weather be like today?"
   • Ca website that uses a knowledge base to interactively respond to users' questions
   • Dassembly line machinery that autonomously inserts headlamps into cars

   Show answer

   Answer: BC

   Next question

7. Question 27 · 236 in bank

   Select 2

   You have an AI solution that provides users with the ability to control smart devices by using verbal commands. Which two types of natural language processing (NLP) workloads does the solution use? Each correct answer presents part of the solution. NOTE: Each correct selection is worth one point.

   • Atext-to-speech
   • Bkey phrase extraction
   • Cspeech-to-text
   • Dlanguage modeling
   • Etranslation

   Show answer

   Answer: CD

   Explanation

   This should be speech-to-text and language modeling. You need to use language modeling to determine the intent of the utterance and to perform an action based on that intent.

   Source: Adapted from community discussion — ThariCD

   References

   • Microsoft Learn

   Next question

8. Question 28 · 236 in bank

   HOTSPOT - For each of the following statements, select Yes if the statement is true. Otherwise, select No. NOTE: Each correct selection is worth one point. Hot Area:

   

   This is an interactive task on the real exam — a drag-and-drop, hotspot or ordering question. There is nothing to select here, so the answer is shown below for reference.

   Show the answer figure

   Answer: See figure below

   Explanation

   Box 1: Yes - Azure Cognitive Service for Language provides features including: * Language detection: This pre-configured feature evaluates text, and determines the language it was written in. It returns a language identifier and a score that indicates the strength of the analysis. Box 2: No - Handwritten detection is part of OCR (Optical Character Recognition). Box 3: Yes - Azure Cognitive Service for Language provides features including: * Named Entity Recognition (NER): This pre-configured feature identifies entities in text across several pre-defined categories. Note: Named entity recognition is a natural language processing technique that can automatically scan entire articles and pull out some fundamental entities in a text and classify them into predefined categories. Entities may be, Organizations, Quantities, Monetary values, Percentages, and more. People's names - Company names - Geographic locations (Both physical and political) Product names - Dates and times - Amounts of money - Names of events - Reference: https://docs.microsoft.com/en-us/azure/cognitive-services/language-service/overview

   Source: Adapted from community discussion — Murtuza

   

   Next question

9. Question 29 · 236 in bank

   DRAG DROP - You plan to use Azure Cognitive Services to develop a voice controlled personal assistant app. Match the Azure Cognitive Services to the appropriate tasks. To answer, drag the appropriate service from the column on the left to its description on the right. Each service may be used once, more than once, or not at all. NOTE: Each correct selection is worth one point. Select and Place:

   

   This is an interactive task on the real exam — a drag-and-drop, hotspot or ordering question. There is nothing to select here, so the answer is shown below for reference.

   Show the answer figure

   Answer: See figure below

   Explanation

   Box 1: Speech - The Speech service provides speech-to-text and text-to-speech capabilities with an Azure Speech resource. You can transcribe speech to text with high accuracy, produce natural-sounding text-to-speech voices, translate spoken audio, and use speaker recognition during conversations. Box 2: Language service - Build applications with conversational language understanding, a Cognitive Service for Language feature that understands natural language to interpret user goals and extracts key information from conversational phrases. Create multilingual, customizable intent classification and entity extraction models for your domain- specific keywords or phrases across 96 languages. Box 3: Speech - Incorrect: Not Translator text: Text translation is a cloud-based REST API feature of the Translator service that uses neural machine translation technology to enable quick and accurate source-to-target text translation in real time across all supported languages. Reference: https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/overview https://azure.microsoft.com/en-us/services/cognitive-services/conversational-language-understanding/ https://docs.microsoft.com/en-us/azure/cognitive-services/translator/text-translation-overview

   

   Next question

10. Question 30 · 236 in bank

    You need to build an app that will read recipe instructions aloud to support users who have reduced vision. Which version service should you use?

    • ALanguage service
    • BTranslator
    • CSpeech
    • DPersonalizer

    Show answer

    Answer: C

    Next question

Keyboard:J Kmove between questionsA–Dselect an answerRshow or hide the answer← →change page

AI-900 practice, question 21. 236 questions available.