AI-102 practice questions 171–180

1. Question 171 · 328 in bank

   HOTSPOT - You are building an app by using the Speech SDK. The app will translate speech from French to German by using natural language processing. You need to define the source language and the output language. How should you complete the code? To answer, select the appropriate options in the answer area. NOTE: Each correct selection is worth one point.

   

   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

   e.v.i.l question. A person who worked with it will go fast and select recognition and synthesis as the answer. But Microsoft made the second one a function call and with their bad naming convention added a new term "targetLanguage". Now you have to remember that mistake of Microsoft

   Source: Adapted from community discussion — famco

   

   Next question

2. Question 172 · 328 in bank

   DRAG DROP - You have a collection of Microsoft Word documents and PowerPoint presentations in German. You need to create a solution to translate the files to French. The solution must meet the following requirements: • Preserve the original formatting of the files. • Support the use of a custom glossary. You create a blob container for German files and a blob container for French files. You upload the original files to the container for German files. Which three actions should you perform in sequence to complete the solution? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order.

   

   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

   IMHO the answer is: 1. Upload a Glossary file to the french files container 2. Define a document translation specification that has french target 3. Perform asynchronous translation by using the document specification As you can see below the glossary is needed before the translation: https://learn.microsoft.com/en-us/azure/ai-services/translator/document-translation/how-to-guides/create-use-glossaries And DocumentTranslationInput is the class we can use for the translation: https://learn.microsoft.com/en-us/python/api/azure-ai-translation-document/azure.ai.translation.document.documenttranslationinput?view=azure-python

   Source: Adapted from community discussion — rdemontis

   References

   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn

   

   Next question

3. Question 173 · 328 in bank

   You have the following C# function.

   

   You call the function by using the following code.

   

   Which output will you receive?

   • AThe quick - The lazy
   • Bthe quick brown fox jumps over the lazy dog
   • Cjumps over the
   • Dquick brown fox lazy dog

   Show answer

   Answer: D

   References

   • Microsoft Learn

   Next question

4. Question 174 · 328 in bank

   You have the following Python method.

   

   You need to deploy an Azure resource to the East US Azure region. The resource will be used to perform sentiment analysis. How should you call the method?

   • Acreate_resource("res1", "TextAnalytics", "Standard", "East US")
   • Bcreate_resource("res1", "ContentModerator", "S0", "eastus")
   • Ccreate_resource("res1", "ContentModerator", "Standard", "East US")
   • Dcreate_resource("res1", "TextAnalytics", "S0", "eastus")

   Show answer

   Answer: D

   Explanation

   The correct answer can be found by a process of elimination: 1. Need to provide reference to correct service -> Text Analytics 2. Need to provide reference to a correct service tier: S0 or F0 3. Need to provide reference to a correct name for a computer region: United States: East US: eastus East US 2: eastus2 Central US: centralus North Central US: northcentralus South Central US: southcentralus West US: westus West US 2: westus2 D is the only answer that captures all these correctly.

   Source: Adapted from community discussion — PeteColag

   Next question

5. Question 175 · 328 in bank

   DRAG DROP - You develop a Python app named App1 that performs speech-to-speech translation. You need to configure App1 to translate English to German. How should you complete the SpeechTranslationConfig object? To answer, drag the appropriate values to the correct targets. Each value may be used once, more than once or not at all. You may need to drag the split bar between panes or scroll to view content. NOTE: Each correct selection is worth one point.

   

   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

   There is a distinction between speech-to-speech translation and speech-to-text-to-speech translation. Some questions refer natural language processing (NLP) and this simple mention changes the approach completely. Based on my experience, speech-to-speech translation requires both SpeechRecognitionLanguage and SpeechSynthesisLanguage. However, when performing speech-to-text-to-speech translation—where NLP is implicitly involved, since the speech is first converted to text before translation—you also need to specify the AddTargetLanguage. In this particular case, the answer would be: SpeechRecognitionLanguage and SpeechSynthesisLanguage because there is no mention to NLP.

   Source: Adapted from community discussion — Skyhawks

   References

   • Microsoft Learn

   

   Next question

6. Question 176 · 328 in bank

   HOTSPOT - You are developing a streaming Speech to Text solution that will use the Speech SDK and MP3 encoding. You need to develop a method to convert speech to text for streaming MP3 data. How should you complete the code? To answer, select the appropriate options in the answer area. NOTE: Each correct selection is worth one point.

   

   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

   first one has to configure the format as MP3, so "AudioStreamFormat" option is chosen. Second, since it is speech to text, the SpeechRecognition option is needed. The answer is CORRECT

   Source: Adapted from community discussion — evangelist

   

   Next question

7. Question 177 · 328 in bank

   DRAG DROP - You train a Custom Vision model used in a mobile app. You receive 1,000 new images that do not have any associated data. You need to use the images to retrain the model. The solution must minimize how long it takes to retrain the model. Which three actions should you perform in the Custom Vision portal? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order. 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

   The given answer is incorrect. The question emphasizes two things - 1) the model has already been trained 2) the solution should be expedient. The given answer will be very slow to manually tag 1,000 images. instead: 1.) upload all the images 2.) Get suggested tags 3.) Review the suggestions and confirm the tags reference: https://docs.microsoft.com/en-us/azure/cognitive-services/custom-vision-service/suggested-tags

   Source: Adapted from community discussion — SuperPetey

   References

   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn
   • Microsoft Learn

   

   Next question

8. Question 178 · 328 in bank

   HOTSPOT - You are building a chatbot. You need to use the Content Moderator API to identify aggressive and sexually explicit language. Which three settings should you configure? To answer, select the appropriate settings in the answer area. NOTE: Each correct selection is worth one point.

   

   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

   Resource Name: Provide the name of your Content Moderator resource. Classify: Set to true to enable classification of content. Ocp-Apim-Subscription-Key: Provide your subscription key for authentication. All other fields are not necessary to set.

   Source: Adapted from community discussion — PeteColag

   References

   • Microsoft Learn

   

   Next question

9. Question 179 · 328 in bank

   You are developing an app that will use the Decision and Language APIs. You need to provision resources for the app. The solution must ensure that each service is accessed by using a single endpoint and credential. Which type of resource should you create?

   • ALanguage
   • BSpeech
   • CAzure Cognitive Services
   • DContent Moderator

   Show answer

   Answer: C

   Explanation

   This question is depricated. Azure Cognitive services is now Azure AI services. I can't find any info about the Decision API but Language API resides within the new AI Services. So for the options: A) Part of Azure AI Services B) Part of Azure AI Services C) Renamed to Azure AI Services D) Part of Azure AI Services, but renamed to Content Safety

   Source: Adapted from community discussion — chrillelundmark

   Next question

10. Question 180 · 328 in bank

    You are building a chatbot. You need to ensure that the bot will recognize the names of your company’s products and codenames. The solution must minimize development effort. Which Azure Cognitive Service for Language service should you include in the solution?

    • Acustom text classification
    • Bentity linking
    • Ccustom Named Entity Recognition (NER)
    • Dkey phrase extraction

    Show answer

    Answer: C

    Explanation

    C. custom Named Entity Recognition (NER) Custom NER allows you to train a model to recognize specific terms relevant to your business, such as product names and codenames. https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/concept-shelf-analysis

    Source: Adapted from community discussion — GHill1982

    References

    • Microsoft Learn

    Next question

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

AI-102 practice, question 171. 328 questions available.