IN NLP – NER

Named Entity Recognition (NER): 
This is a subtask of information extraction that involves locating and classifying named entities in unstructured text into predefined categories. 

Examples of categories: 
Person names, organizations, locations, dates, quantities, and monetary values. 

How it works: 
NER systems are trained to recognize these entities and sort them into a helpful classification system. 

Applications: 
It helps businesses and organizations sift through large volumes of text more efficiently. 

Python Code using nltk

import nltk

nltk.download("averaged_perceptron_tagger")

nltk.download("punkt")

nltk.download("maxent_ne_chunker")

nltk.download("words")

text="Apple Inc. was founded by Steve Jobs and Steve Wozniak in 1976."

# tokenize the text

tokens=nltk.word_tokenize(text)

print(tokens)

# apply pos tagging

pos_tag=nltk.pos_tag(tokens)

named_entities=nltk.ne_chunk(pos_tag)

# print named entity

for entity in named_entities:

     if isinstance(entity,nltk.Tree):

         entity_name=" ".join(word for word,pos in entity.leaves())

        print(entity_name)

Using Spacy

import spacy

nlp=spacy.load("en_core_web_sm")

text="Apple Inc. was founded by Steve Jobs and Steve Wozniak in 1976."

doc=nlp(text)

for entity in doc.ents:

    print(f"{entity.text} ({entity.label_})")

Leave a Reply

Your email address will not be published. Required fields are marked *