Exam AI-102 All QuestionsBrowse all questions from this exam
Question 182

You are building an Azure AI Language Understanding solution.

You discover that many intents have similar utterances containing airport names or airport codes.

You need to minimize the number of utterances used to train the model.

Which type of custom entity should you use?

    Correct Answer: A

    To minimize the number of utterances used to train the model while dealing with similar utterances containing airport names or airport codes, you should use a type of custom entity that can generalize the variations of the entities within the utterances. The ideal choice in this scenario is Pattern.any. Pattern.any entities are used to handle cases where there is a specific pattern in the utterances, but the specific instances of the entity (such as airport names or codes) can vary widely. By using Pattern.any, you can create patterns that recognize and extract any airport name or code without needing to provide all possible variations in the training data.

Discussion
Toby86Option: A

A. Pattern Any From: https://learn.microsoft.com/en-us/azure/ai-services/luis/concepts/patterns-features#patternany-entity For Airports this means: You can exrpess the Airport Name in Full as "John F. Kennedy International Airport" or in short with the code as "JFK" LUIS will have to get both as the same

krzkrzkraOption: A

as per chat gpt: To minimize the number of utterances used to train the model while dealing with similar utterances containing airport names or airport codes, you should use a custom entity that can generalize the variations of the entities within the utterances. The correct choice in this scenario is Pattern.any. Pattern.any is used in Language Understanding (LUIS) to handle cases where you have a specific pattern in the utterances, but the specific instances of an entity (like airport names or codes) can vary widely. By using Pattern.any, you can define a pattern that recognizes and extracts any airport name or code without needing to provide all possible variations in the training data. Therefore, the most suitable option is: A. Pattern.any