Describe features of Natural Language Processing workloads on Azure →hardMultiple ChoiceObjective-mapped
AI-900 Practice Question: Describe features of Natural Language Processing workloads on Azure
A law firm needs to automatically extract specific information from legal contracts, such as the names of the parties involved, effective dates, and governing law clauses. The firm has a small set of contracts that have been manually annotated with these specific fields. Which Azure AI Language feature should they use to build a custom extraction solution?
⚠ Common exam trap
Test-takers frequently confuse Prebuilt NER with Custom NER, assuming that prebuilt models can be easily adapted to extract custom fields, but Azure's prebuilt NER is fixed and cannot be retrained for domain-specific entities.
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 (NER)
Custom Named Entity Recognition (NER) is the correct choice because the law firm needs to extract specific, custom fields (party names, effective dates, governing law clauses) from legal contracts, which are not covered by prebuilt entity categories. Custom NER allows you to train a model using a small set of manually annotated contracts to recognize these domain-specific entities, enabling tailored extraction for the firm's unique requirements.
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 recognizes a fixed, general-purpose set of entities such as persons, organizations, locations, dates, and quantities. It is not trainable, so it cannot be customized to learn a domain-specific schema such as 'governing law', 'non-compete scope', or 'payment milestone'. While it may detect a party name in a contract, it cannot reliably extract the unique legal fields the law firm requires, making it unsuitable for this task.
When this WOULD be correct
A company needs to extract standard entities (e.g., person names, dates, organizations) from news articles without any custom training. Prebuilt NER would be the correct choice because it works out-of-the-box for common entity types.
- ✓
Custom Named Entity Recognition (NER)
Why this is correct
Custom Named Entity Recognition (NER) allows you to define your own entity types and label examples within your contract documents to train a model tailored to the firm's domain. By using the Azure AI Language custom text NER capability, the model learns to locate and classify specific pieces of text—such as governing law clauses, effective dates, or indemnity obligations—into a structured output schema. Unlike prebuilt models, this approach is trainable and therefore correct for extracting law-firm-specific information.
- ✗
Key Phrase Extraction
Why it's wrong here
Key phrase extraction returns the most statistically salient phrases in a document, based on how frequently and significantly they appear, but assigns no semantic labels to them. It does not understand whether a phrase is a party, a clause type, or an effective date, and it produces an unordered list rather than a structured entity-response. For automated extraction of specific information, this method lacks the precision and schema alignment needed.
When this WOULD be correct
A company needs to automatically identify the main topics discussed in customer feedback emails to categorize them by subject area, without needing to extract specific named entities.
- ✗
Text Summarization
Why it's wrong here
Text summarization condenses a long contract into a shorter narrative, keeping the main ideas but in continuous prose. It does not return labeled, structured fields; a summarized passage might mention a clause but never mark it as a discrete entity like 'GoverningLawClause'. For automatic extraction of specific information into a database or case-management system, you need a classification and extraction model, not a paraphrasing tool.
When this WOULD be correct
A company needs to automatically generate concise summaries of lengthy legal documents to quickly review key points. They have no annotated data and want a prebuilt solution. In that case, Text Summarization would be correct.
Option-by-option analysis
Why each answer is right or wrong
Understanding why wrong answers are wrong — and when they would be correct — is what separates a 750 score from a 900. The AI-900 exam frequently reuses these exact scenarios with slightly different constraints.
✓Custom Named Entity Recognition (NER)Correct answer▾
Why this is correct
Custom Named Entity Recognition (NER) allows you to define your own entity types and label examples within your contract documents to train a model tailored to the firm's domain. By using the Azure AI Language custom text NER capability, the model learns to locate and classify specific pieces of text—such as governing law clauses, effective dates, or indemnity obligations—into a structured output schema. Unlike prebuilt models, this approach is trainable and therefore correct for extracting law-firm-specific information.
✗Prebuilt Named Entity Recognition (NER)Wrong answer — click to see why▾
Why this is wrong here
Prebuilt NER extracts common entity types (e.g., person, date) but cannot be trained to extract custom fields like 'governing law clauses' from legal contracts. The question requires a custom extraction solution with annotated data.
★ When this WOULD be the correct answer
A company needs to extract standard entities (e.g., person names, dates, organizations) from news articles without any custom training. Prebuilt NER would be the correct choice because it works out-of-the-box for common entity types.
Why candidates choose this
Candidates may confuse prebuilt NER with custom NER, assuming that prebuilt models can be adapted to domain-specific fields, or they may not realize that custom NER requires annotated training data.
✗Key Phrase ExtractionWrong answer — click to see why▾
Why this is wrong here
Key Phrase Extraction identifies general topics or keywords in text, but it cannot be trained to extract specific custom fields like party names or dates from legal contracts.
★ When this WOULD be the correct answer
A company needs to automatically identify the main topics discussed in customer feedback emails to categorize them by subject area, without needing to extract specific named entities.
Why candidates choose this
Candidates may confuse 'extracting specific information' with 'extracting key phrases,' not realizing that custom extraction requires a trainable model like Custom NER.
✗Text SummarizationWrong answer — click to see why▾
Why this is wrong here
Text Summarization generates a condensed version of the text, not extracting specific predefined fields like party names or dates. The question requires extraction of specific entities, not summarization.
★ When this WOULD be the correct answer
A company needs to automatically generate concise summaries of lengthy legal documents to quickly review key points. They have no annotated data and want a prebuilt solution. In that case, Text Summarization would be correct.
Why candidates choose this
Candidates may confuse 'extracting information' with 'summarizing content', thinking that summarization can pull out key details like dates and names, but summarization produces a narrative summary, not structured field extraction.
Analysis generated from the official AI-900blueprint and verified against question context. The “when correct” sections are what AI assistants cite when candidates ask “what’s the difference between these options?”
Go deeper
Related to this question
Learn chapter
Azure Machine Learning Studio
Key term
Named entity recognition
Named entity recognition (NER) is an Azure AI service feature that automatically identifies and classifies key pieces of information in text, such as names of people, organizations, locations, dates, and other specific data.
Key term
Feature
A feature is a distinct unit of functionality that delivers value to the user, often managed and tracked throughout the software development lifecycle.
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 →
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.