AI-102 Plan and manage an Azure AI solution Practice Question
Your Azure AI Language custom entity recognition model incorrectly extracts 'Microsoft' as an organization when it refers to the company, but fails to extract 'Microsoft' as a product when it refers to the software. How should you improve the model?
⚠ Common exam trap
Test-takers frequently think reducing data or removing entity types simplifies the problem, but Azure AI Language models require diverse, labeled examples with context to handle polysemy (same word, different meanings).
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
✓
Label 'Microsoft' as both 'Organization' and 'Product' in different training sentences with appropriate context
Custom entity recognition models in Azure AI Language learn to distinguish entity types based on context. By labeling 'Microsoft' as 'Organization' in sentences where it refers to the company and as 'Product' in sentences where it refers to the software, you provide the model with the contextual clues needed to disambiguate the same token across different uses. This supervised learning approach directly addresses the model's failure to recognize the product entity.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Reduce the amount of training data to avoid confusion
Why it's wrong here
Reducing training data removes the contextual examples that teach the model to separate the organization and product senses, worsening the confusion. More labelled, context-rich utterances are needed; smaller datasets suit quick prototyping, not resolving ambiguous entity overlap.
- ✗
Remove the 'Organization' entity type from the model
Why it's wrong here
Deleting the Organization entity type removes the model's ability to label genuine company mentions, without teaching it to recognise the product sense. Entity types are the labels being disambiguated, so removal destroys capability rather than resolving context-dependent overlap.
- ✗
Add more training sentences without labeling the entity type
Why it's wrong here
Unlabelled sentences provide no supervised signal about which 'Microsoft' occurrence maps to which entity type, so the model cannot learn the contextual distinction. Labelled examples of each sense are required; unlabelled text suits pretraining or vocabulary coverage instead.
- ✓
Label 'Microsoft' as both 'Organization' and 'Product' in different training sentences with appropriate context
Why this is correct
Custom entity recognition learns from labelled context, so the same surface form can map to different entity types. Labelling 'Microsoft' as Organization in company-context sentences and Product in software-context sentences teaches the model to disambiguate by surrounding words.
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 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.