Implement natural language processing solutions →easyMultiple ChoiceObjective-mapped

AI-102 Practice Question: Implement natural language processing solutions

Exhibit

{
  "displayName": "CustomQuestionAnsweringProject",
  "language": "en",
  "description": "QnA for HR policies",
  "qnaDocuments": [
    {
      "id": "doc1",
      "source": "HR_Handbook.pdf",
      "questions": [
        {
          "question": "What is the vacation policy?",
          "answer": "Employees accrue 15 days per year."
        }
      ]
    }
  ]
}

Refer to the exhibit. You have a Custom Question Answering project configured with the JSON shown. When you test the project in Azure AI Language Studio, the query 'How many vacation days do I get?' returns no answer. What is the most likely cause?

⚠ Common exam trap

A common misconception is that 'no answer' results in Azure AI Language Studio are due to high confidence thresholds or empty answer fields. However, in this scenario, the issue is that the query does not exactly match any trained question in the Custom Question Answering project, so the service does not return an answer.

Answer choices

Why each option matters

Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.

Correct answer & explanation

✓

The query is not phrased as an exact match to the trained question.

Custom Question Answering can be configured to require exact matching between the user query and the trained questions. In the exhibit, the JSON likely defines a QnA pair with a specific question, but the test query 'How many vacation days do I get?' does not exactly match the trained question (e.g., it might be slightly different wording). Since the project is set to exact match, the service returns no answer because the query is not an exact match. Option A correctly identifies this cause.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

✓
The query is not phrased as an exact match to the trained question.
Why this is correct
Custom Question Answering matches questions based on semantic similarity, but if the phrasing is too different, it may not return an answer.
✗
The language is set to English but the query uses informal language.
Why it's wrong here
The language setting is appropriate; informal language should not cause a total failure.
✗
The answer field is empty in the JSON.
Why it's wrong here
The answer field contains 'Employees accrue 15 days per year.'
✗
The confidence score threshold is set too high.
Why it's wrong here
The exhibit does not show any threshold setting.

Go deeper

AI-102 Practice Question: Implement natural language processing solutions

Exhibit

Why each option matters

Option-by-option breakdown

Related to this question