✔ Scroll down and test yourself — answers are hidden under the “View Answer” button.
Attempt all questions first.
✔️ Click SUBMIT at the end to unlock VIEW ANSWER buttons.
Top 20 Named Entity Recognition (NER) MCQs with Answers
What is Named Entity Recognition (NER) in NLP?
Named Entity Recognition (NER) is a core task in Natural Language Processing (NLP) that identifies and classifies important entities in text into predefined categories such as Person, Location, Organization, Date, Time, and Money. It helps machines understand real-world objects mentioned in unstructured text data.
For example, in the sentence "Elon Musk founded SpaceX in 2002", NER identifies:
- Elon Musk → Person
- SpaceX → Organization
- 2002 → Date
Why is Named Entity Recognition Important?
- Improves information extraction from text
- Used in chatbots and virtual assistants
- Enhances search engines and recommendation systems
- Supports resume parsing and document analysis
- Plays a key role in AI and data science applications
NER MCQs for Practice
Below are 20 carefully selected Named Entity Recognition MCQs with answers and explanations to help you prepare for exams, interviews, and competitive tests in NLP, Machine Learning, and Data Science.
Explanation:
NER extracts entities such as names, locations, organizations, and dates from text and classifies them into predefined categories.
Explanation:
NER identifies real-world entities, not grammatical categories like verbs.
Explanation:
“Apple” refers to a company (organization) rather than a fruit in this context.
Explanation:
BIO tagging marks the beginning, inside, and outside of named entities.
Explanation:
“B” indicates the beginning of a named entity.
Explanation:
BIO tagging labels tokens based on their position within entities.
Explanation:
CRFs are widely used for sequence labeling tasks like NER.
Explanation:
CRFs allow flexible feature engineering without strong independence assumptions.
Explanation:
Transformers like BERT capture contextual meaning effectively for NER.
Explanation:
Tokenization breaks text into smaller units like words or subwords, which are essential for NER processing.
Explanation:
F1-score balances precision and recall, making it the most suitable metric for NER evaluation.
Explanation:
Polysemy refers to words having multiple meanings depending on context, which is a major challenge in NER.
Explanation:
CoNLL-2003 is a standard dataset used for evaluating NER systems.
Explanation:
“O” indicates that the token does not belong to any named entity.
Explanation:
Rule-based systems require manual updates and do not scale well to new domains.
Explanation:
Entity linking maps recognized entities to structured databases like Wikipedia or knowledge graphs.
Explanation:
Features like capitalization and word patterns are strong indicators of named entities.
Explanation:
NER systems must correctly identify and group multiple tokens into a single entity.
Explanation:
Pretrained models like BERT capture deep contextual representations, significantly improving NER performance.
Explanation:
NER is widely used in resume parsing to extract names, skills, organizations, and other structured information.
No comments:
Post a Comment