Which Features Are Available in Azure AI Language's Extractive Summarization?
Which TWO features are available in Azure AI Language's extractive summarization?
Quick Answer
The answer is a ranked list of sentences extracted from the document and a confidence score for each sentence. Azure AI Language’s extractive summarization works by analyzing the source text and selecting the most salient sentences, then ordering them by relevance and assigning a numerical confidence score to indicate how well each sentence represents the core content. On the Microsoft Azure AI Engineer Associate AI-102 exam, this question tests your ability to distinguish extractive from abstractive summarization—a common trap is confusing the two, as abstractive methods generate new sentences while extractive simply ranks existing ones. Remember that extractive summarization never creates new text, categorizes by sentiment, or performs entity recognition; those are separate Azure AI Language features. A quick memory tip: think “extract = existing text, rank, and score” to avoid mixing up the output with other NLP capabilities.
⚠ Common exam trap
Many exam-takers confuse extractive summarization with abstractive summarization or assume it includes sentiment or entity extraction, but Azure AI Language keeps these as separate, distinct features.
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
✓
Confidence scores for each extracted sentence.
Azure AI Language's extractive summarization returns a confidence score for each extracted sentence, indicating the model's certainty that the sentence is important. Option D is correct because the feature outputs a ranked list of sentences extracted from the source document, ordered by their relevance scores.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Confidence scores for each extracted sentence.
Why this is correct
Each sentence has a confidence score indicating its relevance.
- ✗
Identified named entities from the document.
Why it's wrong here
Entity recognition is a separate feature.
- ✗
Sentiment scores for each extracted sentence.
Why it's wrong here
Sentiment analysis is a separate feature.
- ✓
Ranked list of sentences extracted from the document.
Why this is correct
The output is a list of sentences ranked by relevance.
- ✗
Generated abstractive summary.
Why it's wrong here
Extractive summarization does not generate new text.
Go deeper
Related to this question
About these practice questions
Courseiva writes every AI-102 question from scratch — 945 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 →
Same concept, more angles
1 more way this is tested on AI-102
These questions test the same concept from different angles. Work through them to make sure you can recognise it however the exam phrases it.
Variation 1. A team is developing a solution to automatically summarize long documents using Azure AI Language. Which feature should they use?
easy- A.Sentiment analysis.
- B.Key phrase extraction.
- ✓ C.Extractive summarization.
- D.Entity recognition.
Why C: Extractive summarization is the correct feature because it specifically identifies and extracts the most important sentences from a document to create a concise summary. Azure AI Language's extractive summarization uses a ranking model to score sentences based on relevance and informativeness, directly addressing the requirement to automatically summarize long documents.
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.