AI-102 Practice Question: Implement natural language processing solutions
A company uses Azure AI Language's custom named entity recognition (NER) to extract product names from support tickets. They have trained a model with 500 labeled entities across 200 documents. During evaluation, they notice the model has high precision but low recall for a specific product category. What should they do to improve recall for that category?
⚠ Common exam trap
The trap here is thinking that adjusting the confidence threshold or hyperparameters will fix recall, but the real issue is insufficient training examples for the underrepresented entity category.
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
✓
Add more labeled examples of the product category to the training dataset, ensuring they cover different contexts and sentence structures.
Low recall for a specific category means the model is failing to identify many true instances. The most effective solution is to add more labeled examples of that category in diverse contexts, which helps the model learn the patterns. Adjusting thresholds or removing data does not address the underlying data gap.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Add more labeled examples of the product category to the training dataset, ensuring they cover different contexts and sentence structures.
Why this is correct
This is correct because low recall indicates the model is missing many instances of the entity. Adding more labeled examples for that category, especially in varied contexts, helps the model learn to recognize it more consistently. This directly addresses the gap in training data for that specific entity type.
- ✗
Increase the model's confidence threshold for entity extraction to reduce false positives.
Why it's wrong here
Increasing the confidence threshold would likely reduce recall further, as it would require higher confidence to extract an entity. The goal is to improve recall, so lowering the threshold might increase recall at the expense of precision, but that is not the recommended first step. The root cause is insufficient training data, not threshold tuning.
- ✗
Use the model's evaluation metrics to identify and remove documents that contain ambiguous entity mentions.
Why it's wrong here
Removing documents may reduce the training data and potentially harm the model's ability to generalize. Ambiguous mentions can be valuable for learning if labeled correctly. The issue is not ambiguous data but rather a lack of examples for the specific category. Removing data is counterproductive.
- ✗
Retrain the model with a higher learning rate to help it converge faster on the underrepresented category.
Why it's wrong here
Azure AI Language's custom NER training does not expose a learning rate parameter. The training process is managed by the service. Even if it did, a higher learning rate could cause instability. The correct approach is to provide more labeled examples for the category, not to adjust hyperparameters.
Go deeper
Related to this question
About these practice questions
This AI-102 question is part of Courseiva's 761-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Microsoft exam blueprint
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.