AI-102 Practice Question: Implement natural language processing solutions
You are implementing a conversational language understanding (CLU) project in Azure AI Language. Your utterances include entities that are sometimes a single word and sometimes a multi-word phrase, such as 'New York' and 'San Francisco'. You need the model to correctly capture these multi-word entities during training and prediction. Which entity component type should you use?
⚠ Common exam trap
Candidates often confuse list or regex entities, which require explicit patterns or synonyms, with learned entities that generalize from labeled examples.
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
✓
Learned entity component
Learned entity components in CLU are trained from labeled utterances, allowing the model to identify entity spans based on surrounding context. This is the correct choice for multi-word entities such as city names that vary in phrasing and cannot be captured reliably by exact-match lists or fixed regex patterns.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Prebuilt entity component
Why it's wrong here
Prebuilt entities recognize common types such as numbers, dates, and geography, but they are not designed to capture arbitrary multi-word phrases specific to your domain. They also cannot be reliably extended with your own labels, so they fail to capture custom multi-word spans like project names or product codes.
- ✓
Learned entity component
Why this is correct
Learned entities use labeled examples to train the model to recognize entity spans, including multi-word phrases, based on context. This allows the model to generalize to new phrasings such as 'New York' or 'San Francisco' without requiring exact matches in a list.
- ✗
Regex entity component
Why it's wrong here
Regex entities match patterns defined by regular expressions and are best for structured formats like order numbers or postal codes. They cannot learn from context, so they will not generalize to natural-language multi-word phrases such as city names with varying formats.
- ✗
List entity component
Why it's wrong here
A list entity matches exact synonyms from a provided list, so it cannot generalize to unseen multi-word phrases. If a phrase is not in the list, it will not be extracted, and the list must be maintained manually, making it unsuitable for dynamic multi-word entity extraction.
Go deeper
Related to this question
About these practice questions
One of 761 original AI-102 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Microsoft exam blueprint
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.