Implement natural language processing solutions →mediumMultiple Choice

AI-102 Practice Question: Implement natural language processing solutions

Exhibit

{
  "parameters": {
    "projectName": "InvoiceExtractor",
    "deploymentName": "production",
    "api-version": "2023-04-01",
    "body": {
      "analysisInput": {
        "documents": [
          {"id": "1", "language": "en", "text": "Invoice #1234 dated 01/15/2023 for $500.00 from Acme Corp."}
        ]
      },
      "parameters": {
        "modelVersion": "latest"
      }
    }
  }
}

Refer to the exhibit. You send this request to the Azure AI Language Service for custom entity recognition. The response returns no entities. What is the most likely reason?

⚠ Common exam trap

It's easy for candidates to assume the request is valid because it includes text and a language parameter, overlooking that custom entity recognition requires explicit project and deployment identifiers to invoke the trained model.

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 projectName and deploymentName are missing from the body parameters

The Azure AI Language Service for custom entity recognition requires both `projectName` and `deploymentName` in the request body to identify which trained custom model to invoke. Without these parameters, the service cannot route the request to the correct custom model, so it returns no entities. The standard pre-built entity recognition does not require these fields, but custom entity recognition mandates them.

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 text input is too short for entity recognition
Why it's wrong here
Custom entity recognition returns no entities when the request omits the project name and deployment name, not because the text is short; the service handles single sentences. Short input is tempting because some models need context, and it would be correct if the API required minimum token counts.
✗
The language parameter is set incorrectly
Why it's wrong here
The language parameter defaults to English and does not suppress entity extraction; the request fails because projectName and deploymentName are absent from the payload. Setting language is tempting because multilingual models need correct codes, and it would be correct when analysing non-English text with a mismatched language setting.
✗
The model version is not specified
Why it's wrong here
The model version is optional; the service uses the deployed model version automatically. The failure stems from the request missing the required projectName and deploymentName parameters. Specifying a version is tempting because versioning matters for reproducibility, and it would be correct when pinning behaviour across model updates.
✓
The projectName and deploymentName are missing from the body parameters
Why this is correct
Custom entity recognition requests must specify both projectName and deploymentName in the body so the service knows which trained model to invoke. Omitting them means no deployment is resolved, so the response returns an empty entities array.

Go deeper

AI-102 Practice Question: Implement natural language processing solutions

Exhibit

Why each option matters

Option-by-option breakdown

Related to this question