NLP Tutorials - Part 24: Named Entity Recognition

named_entity_recog.py

# !pip install -U spacy
# !python -m spacy download en_core_sm

# Importing the libraries
import spacy
import random

# Creating a dictionary for training data
train_data = [
    ("The pizza in Naples it the best", {'entities' : [(4, 8, 'FOOD'), (13, 18, 'LOC')]}),
    ("India is famous for Taj Mahal and Infosys", {'entities' : [(0, 4, 'LOC'), (20, 28, 'LOC'), (34, 40, 'ORG')]}),
    ("Germany is one of the best countries in Europe", {'entities' : [(0, 6, 'LOC'), (40, 45, 'LOC')]})
]

# Instantiating the NLP piepline 
nlp = spacy.blank('en')
ner = nlp.create_pipe('ner')
nlp.add_pipe("ner", last = True)

# Binding the entities to the NER pipeline
for _, annot in train_data:
    for e in annot.get('entities'):
        ner.add_label(e[2])
     
from spacy.training.example import Example
losses = {}

# Training the NER model
for batch in spacy.util.minibatch(train_data, size=1):
    for text, annotations in batch:
        # create Example
        doc = nlp.make_doc(text)
        example = Example.from_dict(doc, annotations)
        # Update the model
        nlp.update([example], losses=losses, drop=0.5)
    print(losses)
    
# Testing the output
for t,_ in train_data:
    d = nlp(t)
    print('Entities', [(ent.text, ent.label) for ent in doc.ents])