AI-102 Practice Question: Implement natural language processing solutions
You are deploying a custom Named Entity Recognition (NER) model using Azure AI Language. You have 500 labeled documents. After training, the model shows high precision but low recall. Which action is most likely to improve recall?
⚠ Common exam trap
The AI-102 exam often tests the misconception that tuning hyperparameters like epochs or confidence thresholds can fix data quality issues, when in fact the most effective remedy for low recall in custom NER is to improve the training data by adding more diverse and representative labeled examples.
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 covering the missed entities
Adding more labeled examples that cover the missed entities directly addresses the root cause of low recall: the model has not seen enough representative patterns for those entities during training. In Azure AI Language custom NER, the model learns to recognize entities based on the labeled data; insufficient or imbalanced examples for certain entity types cause the model to fail to identify them, lowering recall. Enriching the training set with diverse examples of the underperforming entities gives the model more opportunities to learn their variations, thereby improving recall without sacrificing precision.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Switch to Conversational Language Understanding
Why it's wrong here
CLU is for intent/entity extraction from conversational data, not custom NER.
- ✗
Reduce the confidence threshold for entity extraction
Why it's wrong here
Lowering threshold increases predictions but may also increase false positives; does not specifically improve recall.
- ✓
Add more labeled examples covering the missed entities
Why this is correct
More diverse examples help the model generalize and catch more true entities.
- ✗
Increase the number of training epochs
Why it's wrong here
More epochs may overfit and not necessarily improve recall.
Go deeper
Related to this question
About these practice questions
This AI-102 question is part of Courseiva's 945-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 by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
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.