AI-102 Practice Question: Implement natural language processing solutions
Which TWO components are required to create a custom text classification model in Azure AI Language?
⚠ Common exam trap
Test-takers frequently confuse the required components for custom text classification with those for other Azure AI Language features (like custom question answering or conversational language understanding), leading them to select QnA Maker or LUIS as plausible options when they are not applicable.
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
✓
A set of labeled documents
Option A (a set of labeled documents) is correct because custom text classification in Azure AI Language is a supervised learning feature that requires training data in the form of documents tagged with the custom categories (labels) you want the model to learn. Option C (a project in Azure AI Language) is correct because you must create a custom text classification project in Azure AI Language (via Language Studio or the REST API) to hold your dataset, labels, training configuration, and deployed model. Option B (a QnA Maker knowledge base) is incorrect because QnA Maker is for building question-and-answer bots, not for training custom classification models. Option D (a Language Understanding (LUIS) app) is incorrect because LUIS is a separate conversational language understanding service for intents and entities, not custom text classification. Option E (an Azure Functions app) is incorrect because Azure Functions is a serverless compute service and is not a required component for creating or training a custom text classification model.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
A set of labeled documents
Why this is correct
Custom text classification is a supervised task, so the model learns decision boundaries from human-provided examples. Labelled documents supply those intent or class annotations; without them training cannot begin, making this a mandatory component alongside the Azure AI Language project.
- ✗
A QnA Maker knowledge base
Why it's wrong here
A QnA Maker knowledge base serves question-and-answer matching, not labelled training data for classification. It is tempting because both live under Azure AI Language, and QnA Maker suits FAQ bots answering user questions, whereas custom text classification needs tagged utterances and a project.
- ✓
A project in Azure AI Language
Why this is correct
Azure AI Language organises training data, labels and model versions inside a project resource. The project defines the task type and holds the labelled documents, so it is a prerequisite container for building and deploying any custom text classification model.
- ✗
A Language Understanding (LUIS) app
Why it's wrong here
A LUIS app provides intent and entity extraction for conversational utterances, not the labelled text data custom classification trains on. It is tempting because LUIS also lives in Azure AI Language, and it is the right choice for command or intent recognition rather than document category tagging.
- ✗
An Azure Functions app
Why it's wrong here
An Azure Functions app is compute for hosting custom logic, not a required input to model training. It is tempting because Functions commonly orchestrates calls to Azure AI services, which fits scheduled batch scoring or pipeline glue, but training itself needs labelled data and a Language resource.
Quick reference
Cloud Service Model Comparison
| Model | You Manage | Provider Manages | Examples |
|---|---|---|---|
| IaaS | OS, runtime, apps, data | Hardware, hypervisor, networking | EC2, Azure VMs, GCP Compute Engine |
| PaaS | Apps and data | OS, runtime, middleware, hardware | Elastic Beanstalk, Azure App Service |
| SaaS | Data and settings only | Everything else | Microsoft 365, Salesforce, Workday |
| FaaS / Serverless | Function code only | Infra, scaling, runtime | Lambda, Azure Functions, Cloud Run |
| CaaS | Containers and apps | Kubernetes, OS, hardware | EKS, AKS, GKE |
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 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.