Implement natural language processing solutions →hardMultiple Choice

AI-102 Practice Question: Implement natural language processing solutions

Exhibit

Refer to the exhibit.
```json
{
  "customModels": {
    "entities": [
      {
        "category": "Product",
        "subcategory": "Electronics",
        "name": "Laptop"
      },
      {
        "category": "Product",
        "subcategory": "Electronics",
        "name": "Smartphone"
      }
    ],
    "relations": [
      {
        "relationType": "InstanceOf",
        "source": "Laptop",
        "target": "Electronics"
      },
      {
        "relationType": "InstanceOf",
        "source": "Smartphone",
        "target": "Electronics"
      }
    ]
  }
}
```

Refer to the exhibit. You are defining a custom entity recognition model in Azure AI Language. The exhibit shows a partial configuration. What is the relationship between 'Laptop' and 'Electronics'?

⚠ Common exam trap

Many exam-takers confuse hierarchical 'type-of' relationships with 'part-of' relationships, leading them to incorrectly select Option D, or they assume no relationship exists (Option B) because they overlook the visual hierarchy in the exhibit.

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

✓

Laptop is a type of Electronics.

In Azure AI Language custom entity recognition, you define entity types and subtypes using a hierarchical structure. The exhibit shows 'Laptop' as a child of 'Electronics', meaning Laptop is a subtype or specific type of the broader Electronics category. This allows the model to recognize that any Laptop entity is also an instance of Electronics, enabling more granular classification and downstream processing.

Answer analysis

Option-by-option breakdown

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

✓
Laptop is a type of Electronics.
Why this is correct
The exhibit configures 'Electronics' as a parent entity and 'Laptop' as its child, so the model treats Laptop as a subtype of Electronics. This hierarchical relationship enables extraction of both the specific item and its broader category from text.
✗
There is no defined relationship.
Why it's wrong here
Custom entity recognition in Azure AI Language treats each labelled entity as independent; no hierarchy or parent-child link exists between 'Laptop' and 'Electronics' unless explicitly modelled. A relationship would require a separate entity-linking or custom classification construct, not entity recognition alone.
✗
Electronics is a type of Laptop.
Why it's wrong here
Reversing the taxonomy inverts the exhibit's hierarchy: Electronics is the parent class, Laptop the child, so a laptop is a kind of electronics, not the reverse. It tempts because subsumption relations are symmetric-sounding, and 'type of' phrasing fits either direction grammatically.
✗
Laptop is a part of Electronics.
Why it's wrong here
'Part of' denotes mereological composition (a component inside a whole), whereas the exhibit defines an is-a taxonomy where Laptop inherits from Electronics. It tempts because entity configurations often mix part-of and is-a links, so the label looks plausible without checking the exhibit's relation type.

Go deeper

AI-102 Practice Question: Implement natural language processing solutions

Exhibit

Why each option matters

Option-by-option breakdown

Related to this question