AI-102 Practice Question: Implement natural language processing solutions
You are developing a chatbot for a retail company using Azure AI Language's custom question answering. The chatbot must provide answers from a knowledge base of 500 FAQ documents. Users often ask the same question in different wording, and the chatbot fails to return an answer for paraphrased queries. What is the most effective solution?
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
✓
Enable active learning in the project settings and periodically publish the updated knowledge base.
Enabling active learning in Azure AI Language's custom question answering allows the system to learn from user interactions. It suggests alternative phrasings for existing QnA pairs, which helps answer paraphrased queries without manual effort. Option A is wrong because Direct Line Speech channel is for voice interactions, not improving answer coverage. Option C is wrong because simply adding more documents does not address the paraphrasing issue; it may increase redundancy but not handle different wording of the same question. Option D is wrong because manually adding alternate phrases is time-consuming and not scalable; active learning automates this process by identifying and suggesting variations based on user queries.
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 Azure AI Bot Service's Direct Line Speech channel to improve accuracy.
Why it's wrong here
Direct Line Speech is a channel for low-latency voice interaction; it does not alter how custom question answering matches paraphrased text against the knowledge base. It is tempting when adding speech to a bot, and would be correct if the requirement were spoken input rather than improved semantic matching of written questions.
- ✓
Enable active learning in the project settings and periodically publish the updated knowledge base.
Why this is correct
Active learning logs paraphrased queries that score low confidence, surfacing them for review so you can add alternative question phrasings to each FAQ pair. Republishing applies those additions, letting the model match the varied wording users actually type instead of only the original phrasing.
- ✗
Increase the number of FAQ documents in the knowledge base.
Why it's wrong here
Adding more FAQ documents expands coverage of topics but leaves the underlying lexical matching unchanged, so paraphrased queries still fail. It is tempting because more content appears to improve answers, and would be correct when users ask about subjects absent from the knowledge base rather than rephrasing existing ones.
- ✗
Manually add alternate question phrases to the knowledge base for each QnA pair.
Why it's wrong here
Manually adding alternate phrases is unscalable across 500 documents and cannot anticipate every paraphrase. Custom question answering already performs semantic matching, so the fix is enabling or tuning that capability rather than hand-authoring variants. Manual phrasing suits tiny, static knowledge bases with predictable wording.
Go deeper
Related to this question
About these practice questions
One of 761 original AI-102 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. 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.