Named Entity Recognition (NER)

What is Named Entity Recognition (NER)?

Named Entity Recognition (NER) is a subtask of information extraction in natural language processing that aims to identify and classify named entities within a given text, such as people, organizations, locations, dates, and other entity types. NER is crucial for many NLP applications, including information retrieval, question answering, and relation extraction.

Methods for Named Entity Recognition

  • Rule-based methods: These methods rely on hand-crafted rules and patterns to identify named entities in the text. For example, regular expressions can be used to identify patterns like dates or email addresses.
  • Machine learning methods: Supervised machine learning algorithms, such as decision trees, support vector machines, or neural networks, can be trained on annotated data to recognize named entities.
  • Deep learning methods: Recent advances in deep learning have led to the development of more sophisticated NER models, such as BiLSTM-CRF (Bidirectional Long Short-Term Memory with Conditional Random Fields) or transformer-based models like BERT and RoBERTa.

Types of Named Entities

Named entities can be categorized into various types, some of which include:

  • Persons: Names of individuals, e.g., “John Doe”, “Barack Obama”.
  • Organizations: Names of companies, institutions, political parties, etc., e.g., “Google”, “United Nations”.
  • Locations: Names of geographical places, such as countries, cities, and landmarks, e.g., “New York”, “Eiffel Tower”.
  • Dates and times: Absolute or relative dates and times, e.g., “January 1, 2000”, “next week”.
  • Monetary values: Amounts of money, including currency symbols or abbreviations, e.g., “$100”, “50 euros”.
  • Percentages: Numeric values expressed as a percentage, e.g., “25%”.
  • Miscellaneous: Other named entities that don’t fit into the above categories, such as product names, events, or addresses.

Example: Performing Named Entity Recognition (NER) Using spaCy

  1. First, make sure you have spaCy installed. You can install it using pip:
pip install spacy
  1. Next, download a pre-trained language model. In this example, we’ll use the English model:
python -m spacy download en_core_web_sm
  1. Now, create a Python script ( with the following code:
import spacy

# Load the pre-trained language model
nlp = spacy.load("en_core_web_sm")

# Sample text for NER
text = "Apple Inc. is an American multinational technology company headquartered in Cupertino, California. It was founded by Steve Jobs, Steve Wozniak, and Ronald Wayne in April 1976."

# Process the text with the language model
doc = nlp(text)

# Print the named entities and their labels
for ent in doc.ents:
    print(ent.text, ent.label_)
  1. Run the script:
  1. The output should display the named entities and their labels:
Apple Inc. ORG
American NORP
Cupertino GPE
California GPE
Steve Jobs PERSON
Steve Wozniak PERSON
Ronald Wayne PERSON
April 1976 DATE

In this example, we used spaCy’s pre-trained language model to perform NER on a sample text. The model identified various named entities, such as organizations (ORG), nationalities (NORP), geopolitical entities (GPE), persons (PERSON), and dates (DATE), and labeled them accordingly.

Additional Resources for Named Entity Recognition