CompTIA
Checkpoint
ISC
HP
Dell
EC-Council
EXIN
Fortinet
ITIL®
Juniper
PMI
Microsoft
VMware
Avaya
Google
Salesforce
Amazon
Palo Alto Networks
Certiport
ISC2
All Vendors
  2. Home
  3. Exams
  4. Microsoft
  5. AI-102

Free AI-102 Exam Braindumps (page: 33)

Page 32 of 83
PDF with 329 Questions

You are building a Language Understanding model for an e-commerce platform.
You need to construct an entity to capture billing addresses.
Which entity type should you use for the billing address?

  1. machine learned
  2. Regex
  3. geographyV2
  4. Pattern.any
  5. list

Answer(s): A

Explanation:

A regular expression entity extracts an entity based on a regular expression pattern you provide. It ignores case and ignores cultural variant. Regular expression is best for structured text or a predefined sequence of alphanumeric values that are expected in a certain format. For example:

Incorrect Answers:
C: The prebuilt geographyV2 entity detects places. Because this entity is already trained, you do not need to add example utterances containing GeographyV2 to the application intents. GeographyV2 entity is supported in English culture.
The geographical locations have subtypes:

D: Pattern.any is a variable-length placeholder used only in a pattern's template utterance to mark where the entity begins and ends.
E: A list entity represents a fixed, closed set of related words along with their synonyms. You can use list entities to recognize multiple synonyms or variations and extract a normalized output for them. Use the recommend option to see suggestions for new words based on the current list.


Reference:

https://docs.microsoft.com/en-us/azure/cognitive-services/luis/luis-concept-entity-types



You need to upload speech samples to a Speech Studio project for use in training.
How should you upload the samples?

  1. Combine the speech samples into a single audio file in the .wma format and upload the file.
  2. Upload a .zip file that contains a collection of audio files in the .wav format and a corresponding text transcript file.
  3. Upload individual audio files in the FLAC format and manually upload a corresponding transcript in Microsoft Word format.
  4. Upload individual audio files in the .wma format.

Answer(s): B

Explanation:

To upload your data, navigate to the Speech Studio . From the portal, click Upload data to launch the wizard and create your first dataset. You'll be asked to select a speech data type for your dataset, before allowing you to upload your data.
The default audio streaming format is WAV
Use this table to ensure that your audio files are formatted correctly for use with Custom Speech:


Reference:

https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/how-to-custom-speech-test-and-train



You are developing a method for an application that uses the Translator API.
The method will receive the content of a webpage, and then translate the content into Greek (el). The result will also contain a transliteration that uses the Roman alphabet.
You need to create the URI for the call to the Translator API.
You have the following URI.
https://api.cognitive.microsofttranslator.com/translate?api-version=3.0
Which three additional query parameters should you include in the URI? Each correct answer presents part of the solution.
NOTE: Each correct selection is worth one point.

  1. toScript=Cyrl
  2. from=el
  3. textType=html
  4. to=el
  5. textType=plain
  6. toScript=Latn

Answer(s): C,D,F

Explanation:

C: textType is an optional parameter. It defines whether the text being translated is plain text or HTML text (used for web pages).
D: to is a required parameter. It specifies the language of the output text. The target language must be one of the supported languages included in the translation scope.
F: toScript is an optional parameter. It specifies the script of the translated text.
We use Latin (Roman alphabet) script.


Reference:

https://docs.microsoft.com/en-us/azure/cognitive-services/translator/reference/v3-0-translate



You have a chatbot that was built by using the Microsoft Bot Framework.
You need to debug the chatbot endpoint remotely.
Which two tools should you install on a local computer? Each correct answer presents part of the solution.
NOTE: Each correct selection is worth one point.

  1. Fiddler
  2. Bot Framework Composer
  3. Bot Framework Emulator
  4. Bot Framework CLI
  5. ngrok
  6. nginx

Answer(s): C,E

Explanation:

Bot Framework Emulator is a desktop application that allows bot developers to test and debug bots, either locally or remotely. ngrok is a cross-platform application that "allows you to expose a web server running on your local machine to the internet." Essentially, what we'll be doing is using ngrok to forward messages from external channels on the web directly to our local machine to allow debugging, as opposed to the standard messaging endpoint configured in the Azure portal.


Reference:

https://docs.microsoft.com/en-us/azure/bot-service/bot-service-debug-emulator






Post your Comments and Discuss Microsoft AI-102 exam with other Community members: