nltk使用RegexpParser提取名词

import nltk
from nltk import RegexpParser
from nltk.tokenize import word_tokenize

# 定义名词短语的正则表达式规则
grammar = r"""
  NP: {<DT|JJ|NN.*>+} # 匹配以DT（限定词）、JJ（形容词）、NN（名词）开头的词性序列
"""

# 创建RegexpParser对象
chunk_parser = RegexpParser(grammar)

# 待处理的文本
text = "NLTK is a powerful library for natural language processing."

# 分词
tokens = word_tokenize(text)

# 执行语法解析
tree = chunk_parser.parse(nltk.pos_tag(tokens))

# 提取名词短语
noun_phrases = []
for subtree in tree.subtrees():
    if subtree.label() == 'NP':
        noun_phrases.append(' '.join(word for word, pos in subtree.leaves()))

# 打印提取结果
print(noun_phrases)