Implement Custom Language Models AI-102 Practice Questions (Page 2)

Questions 6–10

1. 6foundation · easy

   In Azure AI Language question answering, how can you enable support for multiple languages?

   • AAdd alternate phrasing in different languages to the same Q&A pair
   • BSet the knowledge base language to 'Multi'
   • CUse a custom translation model within the same knowledge base
   • DCreate a separate knowledge base for each language
   Reveal Solution Discussion Select an answer first
2. 7foundation · easy

   In Azure AI Language question answering, what is used to create a multi-turn conversation flow?

   • AAlternate phrasing lists
   • BFollow-up prompts attached to question-answer pairs
   • CMultiple intents and entities
   • DCustom translation models
   Reveal Solution Discussion Select an answer first
4. 8application · medium

   A company is building a custom language model to handle customer support tickets. They want the model to recognize when a user asks to 'reset password' and also extract the user's account ID from the utterance. The team has already created the 'ResetPassword' intent and the 'AccountID' entity. What should they do next to train the model?

   • AAdd sample utterances that include the 'ResetPassword' intent and label the account ID as the 'AccountID' entity.
   • BDeploy the model to production first, then add utterances based on real user traffic.
   • CTrain the model immediately with the intent and entity definitions, as no additional data is required.
   • DCreate a new entity for each possible account ID value before adding utterances.
   Reveal Solution Discussion Select an answer first
5. 9application · medium

   A custom language model project was accidentally deleted from the Azure resource group. The team has a backup JSON file containing all intents, entities, and utterances. What is the correct way to recover the model?

   • AContact Azure support to recover the deleted project.
   • BCreate a new project in the Language service and import the JSON file, then retrain and redeploy the model.
   • CRestore the deleted resource from the Azure portal's recycle bin.
   • DRecreate the model from scratch using the original training data stored on a local drive.
   Reveal Solution Discussion Select an answer first
6. 10foundation · easy

   What is the primary purpose of training a custom language model?

   • ATo deploy the model to a production endpoint
   • BTo create a backup of the model's configuration
   • CTo test the model against a set of labeled test data
   • DTo improve the model's ability to correctly identify intents and entities from user input
   Reveal Solution Discussion Select an answer first