Extractive Summarization Using Azure AI Language
Your organization runs a popular news website. You want to use Azure AI Language to automatically generate summaries of news articles for the homepage. The summaries must be concise (under 100 words), extractive (selecting key sentences from the article), and available in both English and Spanish. You have a large corpus of articles in both languages. You need to implement a solution that requires minimal custom development and leverages Azure AI Language's prebuilt capabilities. Which approach should you take?
Quick Answer
The correct choice is to use the prebuilt extractive summarization API in Azure AI Language for both languages, specifying the maximum summary length. This approach works because extractive summarization is a prebuilt, no-code capability that selects the most salient sentences directly from the source text, making it ideal for generating concise, fact-based summaries under 100 words without requiring custom model training. Azure AI Language natively supports both English and Spanish for this feature, so you can process your bilingual news corpus with a single API call. On the AI-102 exam, this question tests your ability to distinguish between prebuilt and custom language features, with a common trap being the assumption that extractive summarization requires a custom model—it does not. Remember that extractive summarization pulls existing sentences, while abstractive generates new ones; for news articles needing verbatim accuracy, extractive is the safer bet. A useful memory tip: “Extractive extracts, abstractive invents.”
⚠ Common exam trap
It's easy for candidates to confuse extractive and abstractive summarization, or assume custom training is needed for multi-language support, when Azure AI Language's prebuilt extractive API already handles both languages without customization.
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
✓
Use the prebuilt extractive summarization API in Azure AI Language for both languages, specifying the maximum summary length.
The prebuilt extractive summarization API in Azure AI Language natively supports both English and Spanish, can generate summaries under 100 words by specifying the maximum summary length, and requires no custom development. This directly meets the requirements for concise, extractive summaries with minimal effort.
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 the prebuilt extractive summarization API in Azure AI Language for both languages, specifying the maximum summary length.
Why this is correct
The prebuilt extractive summarization API supports English and Spanish, and allows configuring summary length. It requires no custom model training.
- ✗
Train a custom extractive summarization model using Azure AI Language's custom text summarization feature with labeled data in both languages.
Why it's wrong here
Custom extractive summarization requires labeled data and training, which is more effort than using the prebuilt API, especially since the prebuilt model already supports the required languages.
- ✗
Use the conversation summarization API to summarize each article.
Why it's wrong here
Conversation summarization is optimized for dialogues, not news articles; it may not produce good results.
- ✗
Use the prebuilt abstractive summarization API to generate summaries.
Why it's wrong here
Abstractive summarization generates new sentences that may not be directly extracted from the article, which violates the requirement for extractive summaries.
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. You need to summarize a large document using Azure AI Language. Which feature should you use?
easy- ✓ A.Document summarization
- B.Key phrase extraction
- C.Entity recognition
- D.Sentiment analysis
Why A: Document summarization is the correct feature because it is specifically designed to generate concise summaries of large documents, extracting the most important information. Azure AI Language's document summarization uses extractive or abstractive techniques to produce a summary, directly addressing the requirement to summarize a large document.
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.