AI-102 Practice Question: Implement natural language processing solutions
You are building a custom entity extraction solution using Azure AI Language. You have a small dataset (50 documents) with annotated entities. You need to train a model that can extract similar entities from new documents. What is the best approach?
⚠ Common exam trap
Many candidates assume prebuilt APIs or search skills can be adapted to custom entities, but Azure AI Language requires a dedicated custom NER project for training on your own annotated data.
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
✓
Create a custom NER project in Azure AI Language and train it with your annotated data.
Azure AI Language's custom NER (Named Entity Recognition) feature allows you to train a model using your own annotated dataset. With 50 documents, you have enough labeled data to fine-tune a custom entity extraction model that learns the specific entity types and patterns in your domain, enabling accurate extraction from new documents.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Create a custom NER project in Azure AI Language and train it with your annotated data.
Why this is correct
Custom NER in Azure AI Language trains on your annotated documents, learning entity boundaries specific to your domain. With 50 labelled documents it satisfies the small-dataset constraint, extracting similar entities from new documents without prebuilt model limitations.
- ✗
Use the prebuilt entity recognition API to extract entities.
Why it's wrong here
Prebuilt entity recognition extracts only its fixed category set, so it cannot learn the custom entities annotated in your 50 documents. It is tempting because it needs no training, but it is the right choice only when your entities match Microsoft's predefined types.
- ✗
Use the Conversational PII entity extraction feature.
Why it's wrong here
Conversational PII targets personally identifiable information in conversational transcripts, not arbitrary custom entities, and cannot be trained on your annotated documents. It is tempting because it is a customisable AI Language feature, but it is correct only for redacting PII in chat or call transcripts.
- ✗
Use the built-in entity extraction skill in Azure AI Search.
Why it's wrong here
The Azure AI Search built-in entity extraction skill calls prebuilt models and cannot be trained on your annotated documents, so it will not learn your custom entity types. It is tempting because it integrates into indexing pipelines, but it suits enriching search content with standard entities.
Go deeper
Related to this question
About these practice questions
Courseiva writes every AI-102 question from scratch — 761 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or 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.