Named Entity Recognition (original) (raw)

Last Updated : 16 Dec, 2025

Named Entity Recognition (NER) is a key task in Natural Language Processing (NLP) that focuses on identifying and classifying important information (entities) from text. These entities include names of people, organizations, locations, dates, quantities and more. NER helps convert unstructured text into structured data, making it useful for search engines, chatbots, analytics and decision-making systems.

• Identifies meaningful entities from raw text
• Converts unstructured data into structured form
• Widely used in search, chatbots, healthcare, finance and legal systems

Example of NER

NER helps in detecting specific information and sort it into predefined categories. It plays an important role in enhancing other NLP tasks like part-of-speech tagging and parsing.

**Examples of Common Entity Types

• **Person Names: Albert Einstein
• **Organizations: GeeksforGeeks
• **Locations: Paris
• **Dates and Times: 5th May 2025
• **Quantities and Percentages: 50%, $100

It helps in handling ambiguity by analyzing surrounding words, structure of sentence and the overall context to make the correct classification. It means context can change based on entity’s meaning.

**Example 1:

• Amazon is expanding rapidly (Organization)
• The Amazon is the largest rainforest (Location)

**Example 2:

• Jordan won the MVP award (Person)
• Jordan is a country in the Middle East (Location)

Working of Named Entity Recognition (NER)

Various steps involves in NER and are as follows:

1. **Analyzing the Text: It processes entire text to locate words or phrases that could represent entities.
2. **Finding Sentence Boundaries: It identifies starting and ending of sentences using punctuation and capitalization which helps in maintaining meaning and context of entities.
3. **Tokenizing and Part-of-Speech Tagging: Text is broken into tokens (words) and each token is tagged with its grammatical role which provides important clues for identifying entities.
4. **Entity Detection and Classification: Tokens or groups of tokens that match patterns of known entities are recognized and classified into predefined categories like Person, Organization, Location etc.
5. **Model Training and Refinement: Machine learning models are trained using labeled datasets and they improve over time by learning patterns and relationships between words.
6. **Adapting to New Contexts: A well-trained model can generalize to different languages, styles and unseen types of entities by learning from context.

Methods of Named Entity Recognition

There are different methods present in NER which are:

1. Lexicon Based Method

• Uses a dictionary of known entity names.
• Matches words in text with dictionary entries.
• Needs frequent updates, so less commonly used.

2. Rule Based Method

• Uses predefined rules to extract entities.
• Pattern-based rules focus on word structure.
• Context-based rules use surrounding words.
• Combining both improves accuracy.

3. Machine Learning-Based Method

There are two main types of category in this:

• **Multi-Class Classification: Trains model on labeled examples where each entity is categorized. In addition to labelling model also requires a deep understanding of context which makes it a challenging task for a simple machine learning algorithm.
• **Conditional Random Field (CRF): It is implemented by both NLP Speech Tagger and NLTK. It is a probabilistic model that understands the sequence and context of words which helps in making entity prediction more accurate.

4. Deep Learning Based Method

• **Word Embeddings: Captures the meaning of words in context.
• **Automatic Learning: Deep models learn complex patterns without manual feature engineering.
• **Higher Accuracy: Performs well on large varied datasets.
• **spaCy: Fast, production-ready NLP library
• **NLTK: Educational NLP toolkit
• **Stanford NER: CRF-based Java library
• **Flair: Deep learning-based NLP framework
• **Cloud APIs: Google NLP, Amazon Comprehend, IBM Watson

**Implementation of NER in Python

Step 1: Installing Libraries

Firts we need to install necessary libraries. You can run the following commands in command prompt to install them.

!pip install spacy
!pip install nltk
!python -m spacy download en_core_web_sm

Step 2: Importing and Loading data

We will be using Pandas and Spacy libraries to implement this.

• **nlp = spacy.load("en_core_web_sm"): Loads the pre-trained "en_core_web_sm" SpaCy model and stores it in the variable nlp for text processing tasks. Python `

import pandas as pd import spacy import requests from bs4 import BeautifulSoup nlp = spacy.load("en_core_web_sm") pd.set_option("display.max_rows", 200)

`

Step 3: Applying NER to a Sample Text

We have created some random content to implement this you can use any text based on your choice.

• **doc = nlp(content): Processes text stored in content using the nlp model and stores resulting document object in the variable doc for further analysis.
• **for ent in doc.ents: Iterates through the named entities (doc.ents) identified in the processed document and performs actions for each entity. Python `

content = "Trinamool Congress leader Mahua Moitra has moved the Supreme Court against her expulsion from the Lok Sabha over the cash-for-query allegations against her. Moitra was ousted from the Parliament last week after the Ethics Committee of the Lok Sabha found her guilty of jeopardising national security by sharing her parliamentary portal's login credentials with businessman Darshan Hiranandani." doc = nlp(content) for ent in doc.ents: print(ent.text, ent.start_char, ent.end_char, ent.label_)

`

**Output:

Resulting document

It displays the names of the entities, their start and end positions in the text and their predicted labels.

Step 4: Visualizing Entities

We will highlight the text with their categories using visualizing technique for better understanding.

• **displacy.render(doc, style="ent"): Visualizing named entities in the processed doc object by highlighting them in the text with their respective categories such as person, organization, location etc. Python `

from spacy import displacy displacy.render(doc, style="ent")

`

**Output:

Highlighted text with their categories

Step 5: Creating a DataFrame for Entities

• **entities = [(ent.text, ent.label_, ent.lemma_) for ent in doc.ents]: Creating a list of tuples where each tuple contains the text, label (type) and lemma (base form) of each named entity found in the processed doc object. Python `

entities = [(ent.text, ent.label_, ent.lemma_) for ent in doc.ents] df = pd.DataFrame(entities, columns=['text', 'type', 'lemma']) print(df)

`

**Output:

Text after categorization

Here dataframe provides a structured representation of the named entities, their types and lemmatized forms. NER helps organize unstructured text into structured information making it a useful for a wide range of NLP applications.

Applications of NER

• Search engines and information retrieval
• Chatbots and virtual assistants
• News article classification
• Healthcare and biomedical research
• Finance and fraud detection
• Legal document analysis
• Social media monitoring

Which of the following is NOT typically recognized as an entity in NER?

• Dates
• Locations
• Adjectives
• Organizations

Explanation:

NER identifies named entities like people, organizations, places, dates, and quantities—not parts of speech like adjectives.

In the sentence “Amazon is expanding rapidly”, what does NER classify "Amazon" as?

• Location
• Organization
• Person
• Product

Explanation:

Here "Amazon" refers to the company, so NER classifies it as an Organization.

Which method of NER uses probabilistic models like Conditional Random Fields (CRF)?

• Lexicon-based method
• Rule-based method
• Machine learning-based method
• Deep learning-based method

Explanation:

Machine learning-based NER methods include classification and CRF models.

Quiz Completed Successfully

Your Score : 2/3

Accuracy : 0%

Login to View Explanation

1/3

1/3 < Previous Next >