- A
Extractive returns a quoted text span; abstractive generates a new synthesised answer
Extractive QA copies relevant text; abstractive QA writes a new answer — abstractive requires deeper language understanding.
- B
Extractive works on short texts; abstractive handles long documents
Why wrong: Document length is unrelated to the extractive/abstractive distinction — both can work on documents of varying length.
- C
Abstractive QA is faster because it doesn't need to search the full document
Why wrong: Abstractive QA typically requires more processing (generation) than extractive (span detection) — speed isn't the defining difference.
- D
Extractive is pre-built; abstractive always requires custom model training
Why wrong: Both are available as pre-built capabilities in Azure AI Language — neither always requires custom training.
Quick Answer
The correct answer is that extractive question answering returns a quoted text span from the source document, while abstractive question answering generates a new, synthesized answer. Extractive QA works by scanning the provided text for the exact phrase that answers the query, then returning that verbatim span, making it reliable for fact-based lookups. In contrast, abstractive QA uses natural language generation to produce a concise, reworded answer that may not appear anywhere in the source, offering more flexibility but requiring deeper language understanding. On the AI-900 exam, this distinction tests your grasp of Azure AI Language’s custom question answering capabilities, where extractive is the default mode and abstractive is an advanced feature. A common trap is confusing abstractive with simply paraphrasing—remember that abstractive creates entirely new sentences, not just reworded excerpts. Memory tip: think “Extractive = Exact quote” and “Abstractive = All-new answer.”
AI-900 Practice Question: Describe features of Natural Language Processing workloads on Azure
This AI-900 practice question tests your understanding of describe features of natural language processing workloads on azure. Match the stated requirement to the specific cloud service, access model, or configuration option — many options are valid in isolation but not for this scenario. After answering, compare your reasoning against the explanation and wrong-answer breakdown below. Once you have made your selection, read the full explanation to reinforce the concept and understand why each distractor is designed to mislead on exam day.
What is 'abstractive question answering' vs 'extractive question answering' in Azure AI Language?
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
Extractive returns a quoted text span; abstractive generates a new synthesised answer
Option A is correct because extractive question answering (QA) identifies and returns a verbatim text span from the source document as the answer, while abstractive QA generates a new, synthesized answer in natural language that may not appear verbatim in the source. Azure AI Language's custom question answering supports both modes, with extractive being the default and abstractive available as an advanced feature.
Key principle: Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Extractive returns a quoted text span; abstractive generates a new synthesised answer
Why this is correct
Extractive QA copies relevant text; abstractive QA writes a new answer — abstractive requires deeper language understanding.
Related concept
Read the scenario before looking for a memorised answer.
- ✗
Extractive works on short texts; abstractive handles long documents
Why it's wrong here
Document length is unrelated to the extractive/abstractive distinction — both can work on documents of varying length.
- ✗
Abstractive QA is faster because it doesn't need to search the full document
Why it's wrong here
Abstractive QA typically requires more processing (generation) than extractive (span detection) — speed isn't the defining difference.
- ✗
Extractive is pre-built; abstractive always requires custom model training
Why it's wrong here
Both are available as pre-built capabilities in Azure AI Language — neither always requires custom training.
Common exam traps
Common exam trap: answer the scenario, not the keyword
The trap here is that candidates often confuse 'abstractive' with 'extractive' based on speed or document length, when the real differentiator is whether the answer is a direct quote (extractive) or a newly generated sentence (abstractive).
Detailed technical explanation
How to think about this question
Under the hood, extractive QA uses a BERT-based model to predict the start and end token positions of the answer span within the context, returning the exact substring. Abstractive QA, on the other hand, employs a sequence-to-sequence transformer (e.g., T5 or BART) that generates a new answer by paraphrasing or condensing information from the source, which can be useful when the answer is not explicitly stated as a contiguous span. In Azure AI Language, the abstractive QA feature is available in the 'question answering' API when the `answerSpan` parameter is set to `false` and the `answerContext` is configured appropriately.
KKey Concepts to Remember
- Read the scenario before looking for a memorised answer.
- Find the constraint that changes the correct option.
- Eliminate answers that are true in general but not in this case.
TExam Day Tips
- Watch for words such as best, first, most likely and least administrative effort.
- Review why wrong options are wrong, not only why the correct option is correct.
Key takeaway
Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.
Real-world example
How this comes up in practice
A cloud solutions architect for a retail company is evaluating services for a new workload. The correct answer here reflects best practice for the specific scenario described — not a general cloud recommendation. Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option. Cloud exam questions reward reading the constraint carefully: the same technology can be right or wrong depending on the use case.
What to study next
Got this wrong? Here's your next step.
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
- →
Describe features of Natural Language Processing workloads on Azure — study guide chapter
Learn the concepts, then practise the questions
- →
Describe features of Natural Language Processing workloads on Azure practice questions
Targeted practice on this topic area only
- →
All AI-900 questions
1,020 questions across all exam domains
- →
Microsoft Azure AI Fundamentals AI-900 study guide
Full concept coverage aligned to exam objectives
- →
AI-900 practice test guide
How to use practice tests most effectively before exam day
Related practice questions
Related AI-900 practice-question pages
Use these pages to review the topic behind this question. This is how one missed question becomes focused revision.
Describe Artificial Intelligence workloads and considerations practice questions
Practise AI-900 questions linked to Describe Artificial Intelligence workloads and considerations.
Describe fundamental principles of machine learning on Azure practice questions
Practise AI-900 questions linked to Describe fundamental principles of machine learning on Azure.
Describe features of computer vision workloads on Azure practice questions
Practise AI-900 questions linked to Describe features of computer vision workloads on Azure.
Describe features of Natural Language Processing workloads on Azure practice questions
Practise AI-900 questions linked to Describe features of Natural Language Processing workloads on Azure.
Describe features of generative AI workloads on Azure practice questions
Practise AI-900 questions linked to Describe features of generative AI workloads on Azure.
AI-900 fundamentals practice questions
Practise AI-900 questions linked to AI-900 fundamentals.
AI-900 scenario practice questions
Practise AI-900 questions linked to AI-900 scenario.
AI-900 troubleshooting practice questions
Practise AI-900 questions linked to AI-900 troubleshooting.
Practice this exam
Start a free AI-900 practice session
Short sessions build daily habit. Longer sessions build exam-day stamina. Try a timed session to simulate real conditions.
FAQ
Questions learners often ask
What does this AI-900 question test?
Describe features of Natural Language Processing workloads on Azure — This question tests Describe features of Natural Language Processing workloads on Azure — Read the scenario before looking for a memorised answer..
What is the correct answer to this question?
The correct answer is: Extractive returns a quoted text span; abstractive generates a new synthesised answer — Option A is correct because extractive question answering (QA) identifies and returns a verbatim text span from the source document as the answer, while abstractive QA generates a new, synthesized answer in natural language that may not appear verbatim in the source. Azure AI Language's custom question answering supports both modes, with extractive being the default and abstractive available as an advanced feature.
What should I do if I get this AI-900 question wrong?
Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.
What is the key concept behind this question?
Read the scenario before looking for a memorised answer.
About these practice questions
Courseiva creates original exam-style practice questions with explanations and wrong-answer analysis. It does not publish real exam questions, exam dumps, or protected exam content. Learn why practice questions differ from exam dumps →
Last reviewed: Jun 11, 2026
This AI-900 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-900 exam.
Question Discussion
Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.
Sign in to join the discussion.