Improving Entity Recall — Custom NER Model in Azure AI Language
This AI-102 practice question tests your understanding of implement natural language processing solutions. Match the stated requirement to the specific cloud service, access model, or configuration option — many options are valid in isolation but not for this scenario. A key principle to apply: recall. Once you have made your selection, read the full explanation to reinforce the concept and understand why each distractor is designed to mislead on exam day.
Exhibit
Refer to the exhibit. You have the following JSON policy from an Azure AI Language custom entity extraction project evaluation:
{
"evaluation": {
"entities": {
"ProductName": {
"precision": 0.92,
"recall": 0.65,
"f1": 0.76
},
"OrderNumber": {
"precision": 0.88,
"recall": 0.90,
"f1": 0.89
},
"Date": {
"precision": 0.95,
"recall": 0.85,
"f1": 0.90
}
}
}
}
Based on the exhibit, which entity should you focus on improving by adding more labeled examples?
Exhibit
Refer to the exhibit. You have the following JSON policy from an Azure AI Language custom entity extraction project evaluation:
{
"evaluation": {
"entities": {
"ProductName": {
"precision": 0.92,
"recall": 0.65,
"f1": 0.76
},
"OrderNumber": {
"precision": 0.88,
"recall": 0.90,
"f1": 0.89
},
"Date": {
"precision": 0.95,
"recall": 0.85,
"f1": 0.90
}
}
}
}
A
Date
Why wrong: High F1 (0.90) indicates good performance.
B
OrderNumber
Why wrong: High recall (0.90) suggests it is performing well.
C
All entities need improvement.
Why wrong: Only ProductName has significantly low recall.
D
ProductName
Low recall (0.65) indicates many ProductName entities are missed.
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
ProductName
The exhibit shows that ProductName has a recall of 0.65, which is lower than the recall for Date (0.98) and OrderNumber (0.99). Low recall indicates that the model is missing many true instances of ProductName. Adding more labeled examples specifically for ProductName will help the model learn its patterns better, improving recall and overall performance. This aligns with the practice of iterative model improvement in custom entity extraction within Azure AI Language.
Key principle: Recall
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
✗
Date
Why it's wrong here
High F1 (0.90) indicates good performance.
✗
OrderNumber
Why it's wrong here
High recall (0.90) suggests it is performing well.
✗
All entities need improvement.
Why it's wrong here
Only ProductName has significantly low recall.
✓
ProductName
Why this is correct
Low recall (0.65) indicates many ProductName entities are missed.
Related concept
Recall
Common exam traps
Common exam trap: answer the scenario, not the keyword
The trap is that candidates may choose 'All entities need improvement' (Option C) because they overlook the recall scores shown in the exhibit. While ProductName has low recall (0.65), Date and OrderNumber have very high recall (0.98 and 0.99), indicating they are already performing well. The pitfall is failing to compare the scores and identify the one entity with significantly lower recall.
Detailed technical explanation
How to think about this question
In Azure AI Language's custom entity extraction, the model uses a transformer-based architecture that learns from labeled spans. Confidence scores reflect the model's probability distribution over entity types; a low score for ProductName suggests high entropy in predictions, often due to varied naming conventions (e.g., 'iPhone 14' vs 'Galaxy S23'). Adding diverse examples reduces ambiguity and sharpens the decision boundary, directly increasing the F1 score for that entity.
KKey Concepts to Remember
Recall
Custom Entity Extraction
TExam Day Tips
→Watch for words such as best, first, most likely and least administrative effort.
→Review why wrong options are wrong, not only why the correct option is correct.
Key takeaway
Recall
Real-world example
How this comes up in practice
A cloud solutions architect for a retail company is evaluating services for a new workload. The correct answer here reflects best practice for the specific scenario described — not a general cloud recommendation. Recall Cloud exam questions reward reading the constraint carefully: the same technology can be right or wrong depending on the use case.
What to study next
Got this wrong? Here's your next step.
Review recall, then practise related AI-102 questions on the same topic to reinforce the concept.
Implement natural language processing solutions — This question tests Implement natural language processing solutions — Recall.
What is the correct answer to this question?
The correct answer is: ProductName — The exhibit shows that ProductName has a recall of 0.65, which is lower than the recall for Date (0.98) and OrderNumber (0.99). Low recall indicates that the model is missing many true instances of ProductName. Adding more labeled examples specifically for ProductName will help the model learn its patterns better, improving recall and overall performance. This aligns with the practice of iterative model improvement in custom entity extraction within Azure AI Language.
What should I do if I get this AI-102 question wrong?
Review recall, then practise related AI-102 questions on the same topic to reinforce the concept.
What is the key concept behind this question?
Recall
About these practice questions
Courseiva creates original exam-style practice questions with explanations and wrong-answer analysis. It does not publish real exam questions, exam dumps, or protected exam content. Learn why practice questions differ from exam dumps →
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
This AI-102 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-102 exam.
Question Discussion
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
Sign in to join the discussion.