Exam AI-102 All QuestionsBrowse all questions from this exam
Go to Exam
Question 155

Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might have more than one correct solution, while others might not have a correct solution.

After you answer a question in this section, you will NOT be able to return to it. As a result, these questions will not appear in the review screen.

You build a language model by using a Conversational Language Understanding. The language model is used to search for information on a contact list by using an intent named FindContact.

A conversational expert provides you with the following list of phrases to use for training.

• Find contacts in London.

• Who do I know in Seattle?

• Search for contacts in Ukraine.

You need to implement the phrase list in Conversational Language Understanding.

Solution: You create a new utterance for each phrase in the FindContact intent.

Does this meet the goal?

    Correct Answer: A

    Creating a new utterance for each phrase in the FindContact intent is a correct approach. This method trains the language model to recognize variations of how users might express the intent to find contacts in different locations, thereby improving the model's accuracy in identifying the FindContact intent. By providing diverse examples of how users might express their request, it enhances the model's ability to understand and classify user queries correctly.

Discussion
evangelistOption: A

A. Yes Creating a new utterance for each phrase in the FindContact intent is a correct approach to implement the phrase list in Conversational Language Understanding. This method trains the language model to recognize variations of how users might express the intent to find contacts in different locations, thereby improving the model's accuracy in identifying the FindContact intent.

evangelist

Yes, creating a new utterance for each phrase in the FindContact intent aligns with the recommended practice for designing applications in Conversational Language Understanding, as detailed in the documentation. This approach helps in accurately capturing the intent by providing diverse examples of how users might express their request, thus enhancing the model's ability to understand and classify user queries correctly. For more detailed guidelines, refer to the section on creating example utterances for each intent in the documentation

zellckOption: B

B is the answer. https://learn.microsoft.com/en-us/azure/cognitive-services/luis/concepts/application-design#create-example-utterances-for-each-intent To start, avoid creating too many utterances for each intent. Once you have determined the intents you need for your app, create 15 to 30 example utterances per intent. Each utterance should be different from the previously provided utterances. Include a variety of word counts, word choices, verb tenses, and punctuation.

fuck_india

This issue is not working because everyone's opinion is 50-50. I don't know the correct answer, so I will be staring at MS Learn when this question comes up on the real exam.Examtopic should scrutinize and post the correct answer.

nanaw770Option: A

It MUST be A.

PCRamirezOption: B

According to Windows Copilot: B. No Creating a new utterance for each phrase in the FindContact intent is not the most efficient approach. Instead, you can use phrase lists in Conversational Language Understanding (LUIS) to group similar phrases together. By defining a phrase list, you can handle variations of the same intent more effectively. In this case, you can create a phrase list containing the cities (London, Seattle, Ukraine) and use it within the FindContact intent. This way, LUIS will recognize any variation of these cities as part of the same intent without creating individual utterances for each location. 😊

demonite

LUIS is deprecated, CLU will handle creating a new utterance for each phrase

TactableOption: B

According to ChatGPT: B. No Explanation: While creating a new utterance for each phrase in the FindContact intent is a step in the right direction, it may not be sufficient to fully meet the goal. To effectively implement the phrase list in Conversational Language Understanding, it's essential to consider variations in how users might express the same intent. The provided phrases cover different scenarios (finding contacts in different locations), but there may be additional variations and nuances to consider. Therefore, merely creating a new utterance for each provided phrase might not capture all possible ways users could express the intent to find contacts. A more comprehensive approach to training the language model might involve incorporating synonyms, alternative phrasings, and potential variations that users might use when searching for contacts.

dimsokOption: A

It's "Yes" actually, not the more efficient way to do it, but it will work

krzkrzkraOption: B

Selected Answer: B

HVardhiniOption: A

A is the correct answer

anjancOption: B

it is B

fuck_india

This issue is not working because everyone's opinion is 50-50. I don't know the correct answer, so I will be staring at MS Learn when this question comes up on the real exam. Examtopic should scrutinize and post the correct answer.

rdemontisOption: B

B. No Creating a new utterance for each phrase in the FindContact intent is not the most efficient approach for implementing the provided phrase list. Instead, you should use phrase list features or entities to capture variations of these phrases more effectively. In Conversational Language Understanding, you can define a phrase list or entity that includes variations of location names like "London," "Seattle," and "Ukraine." By doing this, you allow the model to recognize these location names as entities, making your intent more flexible and capable of handling variations. This approach is much more scalable and less labor-intensive than creating individual utterances for each location. The goal should be met by using phrase lists or entities effectively to capture variations in the input data and improve the model's performance. (ChatGPT)

dimsok

It won't be efficient but it will do the job, I would vote for "Yes"

sl_mslconsultingOption: B

I picked B because you need the entity to retrieve the location from the utterances for you app to be able to know which contacts to retrieve from the store.

sl_mslconsulting

The utterances provided are different enough. But if your picky and insist that you should have at least 15 utterances that you would pick B anyway.

973b658Option: B

B. Same question.