Implement natural language processing solutions →hardMultiple ChoiceObjective-mapped

AI-102 Practice Question: Implement natural language processing solutions

Exhibit

{
  "apiVersion": "2023-04-01",
  "kind": "TextAnalysis",
  "properties": {
    "displayName": "MyTextAnalytics",
    "settings": {
      "sentimentAnalysis": {
        "opinionMining": true
      },
      "entityRecognition": {
        "modelVersion": "latest"
      },
      "keyPhraseExtraction": {
        "modelVersion": "latest"
      },
      "languageDetection": {
        "modelVersion": "latest"
      },
      "piiRecognition": {
        "domain": "phi",
        "piiCategories": ["All"]
      }
    }
  },
  "location": "eastus"
}

Refer to the exhibit. You are configuring an Azure AI Language resource using an ARM template. The settings include PII recognition with domain set to 'phi'. What is the effect of this setting?

⚠ Common exam trap

Test-takers frequently confuse 'phi' (protected health information) with general health entity recognition, leading them to select options that imply detection of health-related entities or additional PII categories, rather than understanding that 'phi' is a specific, restricted subset of PII focused on HIPAA-defined data.

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

✓

It will detect protected health information (PHI) such as medical record numbers.

When you set the domain to 'phi' in PII recognition for Azure AI Language, the service is configured to detect protected health information (PHI) as defined by HIPAA, such as medical record numbers, health plan numbers, and patient names. This is a specialized subset of PII that focuses on health-related sensitive data, not general health entities or standard PII categories. Option D correctly identifies this behavior.

Answer analysis

Option-by-option breakdown

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

✗
It will detect all standard PII categories plus additional health-specific entities.
Why it's wrong here
'phi' domain focuses on health information, not all PII categories.
✗
It will enable the entity recognition model to detect health entities.
Why it's wrong here
Entity recognition is separate from PII recognition.
✗
It will ignore PII detection and only detect health-related entities.
Why it's wrong here
It does not ignore PII; it detects health-related PII.
✓
It will detect protected health information (PHI) such as medical record numbers.
Why this is correct
'phi' domain enables detection of PHI entities.

Go deeper

AI-102 Practice Question: Implement natural language processing solutions

Exhibit

Why each option matters

Option-by-option breakdown

Related to this question