AI-102 Practice Question: Implement natural language processing solutions
You are building a custom text classification solution in Azure AI Language. You have a dataset with 10 categories and 1000 labeled documents. You need to choose the best project type. What should you use?
⚠ Common exam trap
Candidates often confuse Conversational Language Understanding (CLU) with custom text classification, but CLU is specifically for conversational flows (intents and entities) and cannot be used for general document-level classification tasks.
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
✓
Custom text classification (single or multi-label)
Custom text classification (single or multi-label) is the correct project type because you have a labeled dataset with 10 categories and need to train a model to classify text into those specific categories. Azure AI Language provides a custom text classification feature that allows you to train a model using your own labeled data, supporting both single-label and multi-label classification scenarios. This is the only option that enables you to build a bespoke classifier tailored to your 10-category dataset.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Conversational Language Understanding (CLU)
Why it's wrong here
CLU extracts intents and entities from utterances for conversational apps; it does not classify whole documents into custom categories. It would be correct for a chatbot understanding user requests, not for labelling 1000 documents across ten categories.
- ✗
Key Phrase Extraction
Why it's wrong here
Key Phrase Extraction returns salient terms from unstructured text; it assigns no category labels and cannot be trained on your 1000 labelled documents. It suits summarisation or search indexing. Custom text classification is required to map documents to your ten predefined categories.
- ✗
Prebuilt Text Classification API
Why it's wrong here
Prebuilt Text Classification returns fixed taxonomies such as sentiment or spam, so it cannot emit your ten custom categories. It is tempting because it needs no labelled data or training, and would be the right choice when the required labels already exist in a supported prebuilt domain.
- ✓
Custom text classification (single or multi-label)
Why this is correct
Custom text classification supports both single-label and multi-label projects, letting each document map to one or several of the ten categories. This flexibility matches the dataset's structure, whereas other Azure AI Language project types cannot assign categories to documents.
Go deeper
Related to this question
About these practice questions
Courseiva writes every AI-102 question from scratch — 761 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 →
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.