Building a Question Answering Solution from PDFs Using Azure AI Language
A company is implementing a question-answering system using Azure AI Language Service. They have a set of FAQ documents in PDF format. Which feature should they use to automatically generate question-answer pairs?
⚠ Common exam trap
It's easy for candidates to confuse Custom Question Answering with Conversational Language Understanding (CLU), but CLU is for intent classification and entity extraction in dialog flows, not for automatic QnA pair generation from documents.
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
✓
Custom Question Answering
Custom Question Answering (C) is the correct feature because it is specifically designed to ingest semi-structured content like FAQ PDFs and automatically generate question-answer pairs. It uses a built-in extraction pipeline that parses the document structure (e.g., headings, bullet points) to identify likely questions and their corresponding answers, which can then be reviewed and refined in the Azure Language Studio portal.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Key Phrase Extraction
Why it's wrong here
Key Phrase Extraction returns salient terms, not question-answer pairs, so it cannot generate FAQ pairs from PDFs. It is tempting because it processes documents in the same Language Service resource, but it is designed for indexing and search enrichment, not for the custom question answering ingestion that extracts pairs.
- ✗
Extractive Summarization
Why it's wrong here
Extractive Summarization ranks and returns existing sentences from input text; it does not synthesise question-answer pairs from FAQ PDFs. It is tempting because it also consumes documents within Azure AI Language Service, but it is intended for condensing articles into key sentences, not for populating a question answering knowledge base.
- ✓
Custom Question Answering
Why this is correct
Custom Question Answering ingests source documents such as PDFs and automatically generates question-answer pairs from their content, optionally with follow-up prompts. This satisfies the stem's requirement to build a knowledge base from FAQ documents without manually authoring every pair.
- ✗
Conversational Language Understanding
Why it's wrong here
Conversational Language Understanding trains intent and entity models from labelled utterances; it does not ingest PDFs to produce question-answer pairs. It is tempting because it also sits in Azure AI Language Service and handles questions, but it is intended for building conversational intent classifiers, not for FAQ extraction from documents.
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.