Instruction: Describe what NER is and its importance in NLP.
Context: This question is designed to test the candidate's knowledge of a fundamental NLP task that involves identifying and classifying key information in text.
The way I'd explain it in an interview is this: Named Entity Recognition is the task of identifying and labeling spans of text that refer to entities such as people, organizations, locations, dates, products, or other domain-specific categories.
NER is useful because it turns raw text into structured information that can support search, analytics, compliance, knowledge extraction, and downstream reasoning. In practical systems, the hard part is often domain adaptation and boundary precision, not just the definition of the task.
What matters in an interview is not only knowing the definition, but being able to connect it back to how it changes modeling, evaluation, or deployment decisions in practice.
A weak answer says NER finds names in text and ignores labeling, span boundaries, and broader entity types beyond people.