python nltk pos

• • • 用法：
    • • 举个栗子
    • 标签说明：

pos_tags = nltk.pos_tag(words)
words是独立的单词列表

处理一段英文文本（text），进行分词，删除停用词，词性识别。

import nltk
from nltk.tokenize import sent_tokenize, word_tokenize
from nltk.corpus import stopwords
from string import punctuation

text = 'Compatibility of systems of linear constraints over the set of natural numbers.'
# 分词
words_before = word_tokenize(text.lower())

# 删除停用词和标点符号
stopwords = set(stopwords.words('english') + list(punctuation))

words = []
for w in words_before:
    if w not in stopwords:
        words.append(w)

# 词性标注
pos_tags = nltk.pos_tag(words)
print(pos_tags)

输出

[('compatibility', 'NN'), ('systems', 'NNS'), ('linear', 'JJ'), ('constraints', 'NNS'), ('set', 'VBD'), ('natural', 'JJ'), ('numbers', 'NNS')]