命名实体识别介绍

1 初始化数据

paragraph1 = """Please send this message to those people who mean something to 
you,to those who have touched your life in one way or another,to those who make you 
smile when you really need it,to those that make you see the brighter side of things 
when you are really down,to those who you want to let them know that you appreciate 
their friendship.And if you don’t, don’t worry,nothing bad will happen to you,you 
will just miss out on the opportunity to brighten someone’s day with this message.
 """
paragraph2 = 'Beijing, Shanghai, Tianjin'

2 查看nltk的版本

# 查看nltk的版本
import nltk
print('NLTK version: %s' % (nltk.__version__))

输出

3 导入包

# 需要导入的包
from nltk import word_tokenize, pos_tag, ne_chunk

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

输出

4 进行分词

# 进行分词！
results = ne_chunk(pos_tag(word_tokenize(paragraph1)))
print('The sentence is: %s' % (paragraph1))
print()
for x in str(results).split('\n'):
    if '/NNP' in x:
        print(x)

输出1

results = ne_chunk(pos_tag(word_tokenize(paragraph2)))
print(paragraph2)
print()
for x in str(results).split('\n'):
    if '/NNP' in x:
        print(x)

输出2