Courseiva

AI-102 Practice Question: Implement natural language processing solutions

You are building a solution that uses Azure AI Language's question answering (custom question answering) to create a bot that answers employee HR questions. You have created a project and added a knowledge base with 50 question-answer pairs. You need to ensure the bot provides accurate answers and can handle paraphrased questions. Which two actions should you perform? (Choose two.)

⚠ Common exam trap

The trap here is thinking that increasing the confidence threshold improves accuracy, but it actually reduces the bot's ability to match paraphrased questions by making it more conservative.

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 alternative questions for each question-answer pair to cover different ways employees might ask the same question.

To improve paraphrase handling in custom question answering, you should add alternative questions to cover different phrasings and enable active learning to continuously refine the knowledge base based on user queries. Increasing thresholds or adding entities does not help with matching paraphrased questions.

Answer analysis

Option-by-option breakdown

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

  • ✗

    Configure the project to use a different language model for better semantic understanding.

    Why it's wrong here

    Custom question answering does not allow selecting different language models; it uses a built-in semantic ranker. The service automatically handles semantic understanding based on the language of the knowledge base. Changing the model is not a supported action and would not address paraphrase handling. The correct actions are adding alternative questions and using active learning.

  • ✗

    Increase the confidence threshold for answer matching to ensure only high-confidence answers are returned.

    Why it's wrong here

    Increasing the confidence threshold would make the bot more conservative, potentially causing it to return no answer for paraphrased questions. The goal is to handle paraphrases, so you need better coverage, not stricter matching. A high threshold could reduce accuracy by rejecting correct answers that have slightly lower confidence.

  • ✗

    Add a prebuilt entity for 'person' to the project to extract employee names from questions.

    Why it's wrong here

    Custom question answering does not use entities for matching; it uses question-answer pairs and alternative questions. Adding a prebuilt entity is not applicable to question answering projects. The scenario is about answering HR questions, not extracting entities. This action would not improve paraphrase handling.

  • ✓

    Add alternative questions for each question-answer pair to cover different ways employees might ask the same question.

    Why this is correct

    This is correct because alternative questions help the model understand paraphrases. Custom question answering uses these variations to match user queries to the correct answer. By providing multiple phrasings, you improve the likelihood that the bot recognizes a paraphrased question and returns the right answer.

  • ✓

    Enable active learning and regularly review and accept or reject suggested question-answer pairs.

    Why this is correct

    This is correct because active learning uses real user queries to suggest new question variants and answers. By reviewing and accepting relevant suggestions, you continuously improve the knowledge base's coverage and accuracy. This is a recommended practice for maintaining and enhancing a custom question answering project over time.

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 →

How Courseiva writes practice questions · Editorial policy

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.