Describe features of Natural Language Processing workloads on Azure →mediumMultiple ChoiceObjective-mapped
AI-900 Practice Question: Describe features of Natural Language Processing workloads on Azure
What is 'abstractive summarization' vs. 'extractive summarization' in Azure AI Language, and which produces summaries in new words?
⚠ Common exam trap
Many exam-takers confuse the two terms, mistakenly thinking 'abstractive' means 'extracting abstracts' or that 'extractive' creates new content, so they reverse the definitions.
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
✓
Abstractive generates new sentences; extractive selects existing sentences from the source
Abstractive summarization generates new sentences that rephrase the core meaning of the source text, similar to how a human would summarize. Extractive summarization, in contrast, selects and copies key sentences directly from the original document without rewording them. Option B correctly identifies that abstractive produces new sentences while extractive selects existing ones.
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 produces new words; abstractive copies sentences
Why it's wrong here
This definition is reversed. Extractive summarization selects and copies existing sentences or fragments from the source text verbatim, while abstractive summarization generates new words and sentences, often paraphrasing ideas rather than reusing original phrasing. Because the option assigns the opposite behavior to each technique, it is incorrect.
- ✓
Abstractive generates new sentences; extractive selects existing sentences from the source
Why this is correct
This is correct because abstractive summarization uses natural language generation to produce novel sentences that may not appear in the source but convey key information, whereas extractive summarization ranks and returns existing sentences unchanged. Abstractive output tends to be more fluent and concise but can introduce hallucinations; extractive output is faithful to the source but may lack cohesion.
- ✗
They produce identical output through different computational paths
Why it's wrong here
This is wrong because the outputs are fundamentally different in content and lexical form. Extractive summaries are a verbatim subset of source sentences, so every token appears in the original document, while abstractive summaries can contain newly synthesized phrases and reordered ideas not found anywhere in the input. The two methods do not merely compute the same result via different implementation paths.
- ✗
Abstractive works only for legal documents; extractive for general text
Why it's wrong here
This is incorrect because both extractive and abstractive techniques are domain-agnostic and can summarize legal, news, medical, or general text. The choice depends on the desired trade-off between faithfulness and compressiveness—extractive is preferred when exact source evidence is needed, abstractive when natural, concise prose is desired. No legal-only or general-text-only restriction exists.
Go deeper
Related to this question
About these practice questions
This AI-900 question is part of Courseiva's 985-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 →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
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.