Courseiva
Implement natural language processing solutionseasyMultiple SelectObjective-mapped

AI-102 Practice Question: Implement natural language processing solutions

You are building a solution to extract custom entities from legal contracts using Azure AI Language. You have a small set of labeled documents. Which two features should you use to build and improve the custom NER model? (Choose two.)

⚠ Common exam trap

Candidates often confuse active learning with prebuilt model customization (Option B) or assume that key phrase extraction (Option E) can substitute for entity-specific labeling, but Azure AI Language custom NER requires explicit entity definitions and labeled data, not generic key phrases.

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

Use active learning to automatically suggest new labels from unlabeled documents.

Active learning in Azure AI Language automatically identifies unlabeled documents where the model has low confidence and suggests them for labeling, which improves the custom NER model iteratively with minimal manual effort. This feature is specifically designed to reduce the labeling burden while maximizing model accuracy by focusing on the most informative samples.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

  • Use active learning to automatically suggest new labels from unlabeled documents.

    Why this is correct

    Active learning identifies uncertain predictions and suggests them for labeling, reducing manual effort.

  • Use the prebuilt NER model as a base and extend it with custom entities.

    Why it's wrong here

    Custom NER is a separate training process; prebuilt NER cannot be extended.

  • Configure an orchestration workflow to route documents to the best model.

    Why it's wrong here

    Orchestration workflow is for routing to different language understanding models, not for NER improvement.

  • Add synonyms for each entity to improve recognition of variations.

    Why this is correct

    Synonyms help the model identify entities expressed in different ways.

  • Extract key phrases from the documents and use them as features.

    Why it's wrong here

    Key phrase extraction is a separate API and is not used as input to custom NER model training.

About these practice questions

Courseiva writes every AI-102 question from scratch — 945 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 →

How Courseiva writes practice questions · Editorial policy

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.