CODEWITHSUNDEEP
pythonpython-3.xnlpjupyternltk
getintoityuh
getintoityuh

Reputation: 51

NLTK to Identify Names

I am attepmting to extract names with the nltk python module.

import nltk
#!pip install svgling

nltk.download('punkt')
nltk.download('averaged_perceptron_tagger')
nltk.download('maxent_ne_chunker')
nltk.download('words')

import nltk

from nltk import ne_chunk, pos_tag, word_tokenize
from nltk.tree import Tree

text = "Elon Musk 889-888-8888 [email protected] Jeff Bezos (345)123-1234 [email protected] Reshma Saujani [email protected] 888-888-8888 Barkevious Mingo"

nltk_results = ne_chunk(pos_tag(word_tokenize(text)))
for nltk_result in nltk_results:
    if type(nltk_result) == Tree:
        name = ''
        for nltk_result_leaf in nltk_result.leaves():
            name += nltk_result_leaf[0] + ' '
        print ('Type: ', nltk_result.label(), 'Name: ', name)

The output I get from the following code above is as follows:

Type:  PERSON Name:  Elon 
Type:  GPE Name:  Musk 
Type:  PERSON Name:  Jeff Bezos 
Type:  ORGANIZATION Name:  Barkevious Mingo

This is not correct. First of all, Some names are broken up. Farily common ones, too, like Elon Musk. Next, all names are not identified. The desired output would be:

Type:  PERSON Name:  Elon Musk
Type:  PERSON Name:  Jeff Bezos
Type:  PERSON Name:  Reshma Saujani 
Type:  PERSON Name:  Barkevious Mingo

Is there a better option in python?

Upvotes: 1

Views: 1484

Answers (1)

anon
anon

Reputation:

You could give a try to Spacy

import spacy
from spacy import displacy

NER = spacy.load("en_core_web_lg")

raw_text = "Elon Musk 889-888-8888 [email protected] Jeff Bezos (345)123-1234 [email protected] Reshma Saujani [email protected] 888-888-8888 Barkevious Mingo"

text = NER(raw_text)


for word in text.ents:
    print(word.text,word.label_)

Output:

Elon Musk PERSON
889-888 CARDINAL
Jeff Bezos PERSON
345)123 CARDINAL
Reshma Saujani PERSON

Upvotes: 2

Related Questions