Python -如何在NLTK中解析后提取名词短语

import nltk
from nltk.tokenize import word_tokenize
from nltk.corpus import stopwords
from nltk.chunk import RegexpParser

def extract_noun_phrases(text):
    # 分词
    tokens = word_tokenize(text)
    
    # 去除停用词
    stop_words = set(stopwords.words('english'))
    filtered_tokens = [token for token in tokens if token.lower() not in stop_words]
    
    # 词性标注
    tagged_tokens = nltk.pos_tag(filtered_tokens)
    
    # 定义名词短语的语法规则
    grammar = r'NP: {<DT>?<JJ>*<NN>}'
    
    # 创建名词短语解析器
    parser = RegexpParser(grammar)
    
    # 解析文本
    parsed_text = parser.parse(tagged_tokens)
    
    # 提取名词短语
    noun_phrases = []
    for subtree in parsed_text.subtrees():
        if subtree.label() == 'NP':
            noun_phrase = ' '.join(word for word, tag in subtree.leaves())
            noun_phrases.append(noun_phrase)
    
    return noun_phrases

# 示例用法
text = "The quick brown fox jumps over the lazy dog"
phrases = extract_noun_phrases(text)
print(phrases)