python - 从 NTLK pos_tag 中仅删除 'NN' words'

Question

我有一个使用 NLTK 查找名词和动词的代码。

from nltk.corpus import wordnet as wn
from nltk import pos_tag
import nltk


sentence = "Hello my name is Abhishek Mitra"
sentence = nltk.word_tokenize(sentence)
sent = pos_tag(sentence)
print sent

它返回：

[('Hello', 'NNP'), ('my', 'PRP$'), ('name', 'NN'), ('is', 'VBZ'), ('Abhishek', 'NNP'), ('Mitra', 'NNP')]

我怎样才能从列表中只删除“NN”字样。

Answer 1

您可以使用列表推导来删除“NN”元素：

from nltk.corpus import wordnet as wn
from nltk import pos_tag
import nltk

sentence = "Hello my name is Abhishek Mitra"
sentence = nltk.word_tokenize(sentence)
sent = pos_tag(sentence)
print [s for s in sent if s[1] != 'NN']

Answer 2

这是另一种方法（利用元组的优势）：

from nltk.corpus import wordnet as wn
from nltk import pos_tag
import nltk

sentence = "Hello my name is Abhishek Mitra"
sentence = nltk.word_tokenize(sentence)
sent = pos_tag(sentence) 
sent_clean = [x for (x,y) in sent if y not in ('NN')]

print(sent_clean)

输出：

['Hello', 'my', 'is', 'Abhishek', 'Mitra']

说明： 在代码中：

sent_clean = [x for (x,y) in sent if y not in ('NN')]

在您对句子中的每个单词进行 POS 标记后，您将尝试为由于 POS 标记而创建的元组提取单词。您指定提取的条件是第二部分

同样，如果要消除多个 POS：

sent_clean2 = [x for (x,y) in sent if y not in ('PRP$', 'VBZ', 'NN')]

print(sent_clean2)

输出：

['Hello', 'Abhishek', 'Mitra']

Answer 3

我会使用过滤功能：

>>> filter(lambda (word, tag): tag != 'NN', sent)
[('Hello', 'NNP'), ('my', 'PRP$'), ('is', 'VBZ'), ('Abhishek', 'NNP'), ('Mitra', 'NNP')]

Answer 4

a = [('Hello', 'NNP'), ('my', 'PRP$'), ('name', 'NN'), ('is', 'VBZ'), ('Abhishek', 'NNP'), ('Mitra', 'NNP')]

c = [b  for b in a if b[-1] != 'NN']