Courseiva

AI-900 Practice Question: Describe features of Natural Language Processing workloads on Azure

A legal department needs to automatically extract specific entities from contracts, such as 'Effective Date', 'Governing Law', and 'Payment Terms'. They have 500 manually labeled contract clauses that specify which text spans correspond to each entity. Which Azure AI Language feature should they use to build this custom entity extraction solution?

⚠ Common exam trap

Test-takers frequently confuse Prebuilt NER (which works out-of-the-box for common entities) with Custom NER (which requires labeled data but can extract any domain-specific entity), and they may incorrectly choose Prebuilt NER because they assume 'Effective Date' is a standard date entity, ignoring that the question explicitly requires custom entities like 'Governing Law' that are not predefined.

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 Named Entity Recognition (Custom NER)

Custom Named Entity Recognition (Custom NER) is the correct choice because it allows you to train a model on your own labeled data (the 500 manually labeled contract clauses) to extract domain-specific entities like 'Effective Date', 'Governing Law', and 'Payment Terms' that are not covered by prebuilt models. This feature uses a custom trained model to identify and classify text spans according to your defined schema.

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 Named Entity Recognition (NER)

    Why it's wrong here

    Prebuilt Named Entity Recognition in Azure AI Language uses a fixed, pretrained model that assigns labels only from built-in categories such as Person, Organization, Location, and DateTime. Because this model cannot be retrained or extended on private legal data, it will not output custom entities like Governing Law, and the term 'Governing Law' in a contract may be ignored or mislabeled as a generic organization or location. Therefore it is unsuitable for extracting domain-specific legal fields without custom training.

  • Key phrase extraction

    Why it's wrong here

    Key phrase extraction is an unsupervised extractive technique that returns the most relevant standalone words or short phrases from a document, ranked by their salience, but it does not associate those strings with any semantic type or data field. It has no concept of custom entity categories, nor can it be trained to recognize legal concepts such as Governing Law; it might return 'Governing Law' as a phrase, but without labeling it as a value for a field. Because key phrase extraction lacks the structured, typed output required for automated data capture, it is also a wrong answer.

  • Custom Named Entity Recognition (Custom NER)

    Why this is correct

    Custom Named Entity Recognition (Custom NER) is a feature of Azure AI Language that lets you train your own model by tagging spans of text in labeled documents with entity types you define, such as GoverningLaw, EffectiveDate, or PartyName. After a model is trained and deployed, the prediction API extracts these exact spans and their associated types from new contracts, giving structured output suitable for downstream automation. Because it is fine-tuned on legal documents and supports arbitrary entity types, it directly satisfies the requirement to automatically extract specific legal clauses.

  • Custom text classification

    Why it's wrong here

    Custom text classification builds a model that reads an entire document and assigns it a classification label, or multiple labels, based on the overall content—for example, 'Sales Contract' or 'NDA'. It does not locate or return the specific strings or token spans that justify the class, so it cannot be used to extract a value for 'Governing Law' from one sentence. For this reason, although it is a custom, trainable service, it produces document-level output, not entity-level extractions, so this option is wrong.

Go deeper

Related to this question

About these practice questions

This AI-900 question is part of Courseiva's 985-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. Learn why practice questions differ from exam dumps →

How Courseiva writes practice questions · Editorial policy

JA

Written by Johnson Ajibi, MSc IT Security

Senior Network & Security Engineer · founder of Courseiva

This AI-900 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-900 exam.