Question 92 of 1,020

Quick Answer

The correct answer is that span-based named entity recognition identifies text spans as candidate entities and classifies each span, enabling it to handle overlapping and nested entities. Unlike sequence labeling, which assigns a single label per token using methods like BIO tagging, span-based NER first locates contiguous token sequences and then classifies them, allowing it to recognize both "University of Washington" as an organization and "Washington" as a location within the same sentence—a task sequence labeling struggles with due to its flat, token-level approach. On the Microsoft Azure AI-900 exam, this concept tests your understanding of how Azure AI Language’s custom NER works, often appearing in questions about entity extraction capabilities. A common trap is assuming all NER uses sequence labeling; remember that span-based methods excel with hierarchical or overlapping entities. Memory tip: think "spans for stacks"—spans can stack nested entities, while sequence labeling flattens them.

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

This AI-900 practice question tests your understanding of describe features of natural language processing workloads on azure. Read the scenario carefully and evaluate each option against the stated constraints before committing to an answer. After answering, compare your reasoning against the explanation and wrong-answer breakdown below. Once you have made your selection, read the full explanation to reinforce the concept and understand why each distractor is designed to mislead on exam day.

What is 'span-based named entity recognition' and how does it differ from sequence labelling?

Question 1mediummultiple choice
Full question →

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

Identifying text spans as candidate entities and classifying each span — handling overlapping and nested entities

Span-based named entity recognition (NER) identifies candidate entities by first locating text spans (contiguous sequences of tokens) and then classifying each span into an entity type. This differs from sequence labeling (e.g., BIO tagging) because it can naturally handle overlapping and nested entities—for example, recognizing both "University of Washington" as an organization and "Washington" as a location within the same sentence—whereas sequence labeling typically assigns a single label per token and struggles with such hierarchies.

Key principle: Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

  • NER that works across spans (paragraphs) of text rather than single sentences

    Why it's wrong here

    Cross-sentence NER is a document-level concern — span-based NER identifies entity spans within text as units for classification.

  • Identifying text spans as candidate entities and classifying each span — handling overlapping and nested entities

    Why this is correct

    Span-based NER extracts and classifies spans directly — naturally handling overlapping entities that sequence labelling struggles with.

    Related concept

    Read the scenario before looking for a memorised answer.

  • A technique that spans multiple languages to recognise entities in multilingual text

    Why it's wrong here

    Cross-lingual NER is multilingual capability — span-based is an architectural approach to entity detection within a single text.

  • NER that spans multiple documents to track entities across a corpus

    Why it's wrong here

    Cross-document entity tracking is coreference resolution — span-based NER identifies entities within a single document.

Common exam traps

Common exam trap: answer the scenario, not the keyword

The trap here is that candidates confuse 'span' with 'document span' or 'paragraph span' (options A and D) or think it refers to multilingual coverage (option C), when the actual technical distinction is about handling overlapping and nested entities within a single text segment.

Detailed technical explanation

How to think about this question

Under the hood, span-based NER models often use a transformer encoder to produce token embeddings, then enumerate all possible spans up to a maximum length, compute span representations (e.g., via pooling or attention), and classify each span into entity types or 'non-entity'. A subtle behavior is that these models can predict overlapping entities of different types (e.g., a person name inside an organization name) by treating each span independently, whereas sequence labeling with BIO tags would require special tagging schemes (e.g., BILOU) that still cannot represent arbitrary nesting without additional mechanisms. In real-world scenarios like biomedical text mining, span-based NER is critical for extracting nested entities such as "EGFR gene mutation" where "EGFR" is a gene and the whole phrase is a mutation.

KKey Concepts to Remember

  • Read the scenario before looking for a memorised answer.
  • Find the constraint that changes the correct option.
  • Eliminate answers that are true in general but not in this case.

TExam Day Tips

  • Watch for words such as best, first, most likely and least administrative effort.
  • Review why wrong options are wrong, not only why the correct option is correct.

Key takeaway

Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option.

Real-world example

How this comes up in practice

A cloud solutions architect for a retail company is evaluating services for a new workload. The correct answer here reflects best practice for the specific scenario described — not a general cloud recommendation. Answer the scenario, not the keyword: identify the specific constraint before choosing the most familiar-sounding option. Cloud exam questions reward reading the constraint carefully: the same technology can be right or wrong depending on the use case.

What to study next

Got this wrong? Here's your next step.

Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.

Related practice questions

Related AI-900 practice-question pages

Use these pages to review the topic behind this question. This is how one missed question becomes focused revision.

Practice this exam

Start a free AI-900 practice session

Short sessions build daily habit. Longer sessions build exam-day stamina. Try a timed session to simulate real conditions.

FAQ

Questions learners often ask

What does this AI-900 question test?

Describe features of Natural Language Processing workloads on Azure — This question tests Describe features of Natural Language Processing workloads on Azure — Read the scenario before looking for a memorised answer..

What is the correct answer to this question?

The correct answer is: Identifying text spans as candidate entities and classifying each span — handling overlapping and nested entities — Span-based named entity recognition (NER) identifies candidate entities by first locating text spans (contiguous sequences of tokens) and then classifying each span into an entity type. This differs from sequence labeling (e.g., BIO tagging) because it can naturally handle overlapping and nested entities—for example, recognizing both "University of Washington" as an organization and "Washington" as a location within the same sentence—whereas sequence labeling typically assigns a single label per token and struggles with such hierarchies.

What should I do if I get this AI-900 question wrong?

Identify which exam domain this question belongs to, review the core concept, then practise similar questions from the same domain.

What is the key concept behind this question?

Read the scenario before looking for a memorised answer.

About these practice questions

Courseiva creates original exam-style practice questions with explanations and wrong-answer analysis. It does not publish real exam questions, exam dumps, or protected exam content. Learn why practice questions differ from exam dumps →

How Courseiva writes practice questions · Editorial policy

Keep practising

More AI-900 practice questions

Last reviewed: Jun 11, 2026

Question Discussion

Share a tip, memory trick, or ask about the reasoning behind this question. Do not post real exam questions, leaked content, braindumps, or copyrighted exam material. Comments are moderated and may be removed without notice.

Loading comments…

Sign in to join the discussion.

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.