使用Python和NLTK从文本中高效提取名词：一份专业教程

import nltk

# 安装NLTK库（如果尚未安装）
# pip install nltk

# 下载必要的NLTK数据包
try:
    nltk.data.find('tokenizers/punkt')
except nltk.downloader.DownloadError:
    nltk.download('punkt')

try:
    nltk.data.find('taggers/averaged_perceptron_tagger')
except nltk.downloader.DownloadError:
    nltk.download('averaged_perceptron_tagger')

try:
    nltk.data.find('corpora/stopwords')
except nltk.downloader.DownloadError:
    nltk.download('stopwords')

print("NLTK及其必要数据包已准备就绪。")

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

def extract_nouns(text):
    """
    从给定的文本中提取所有名词。

    Args:
        text (str): 待处理的输入文本。

    Returns:
        list: 包含所有提取到的名词的列表。
    """
    extracted_nouns = []

    # 1. 文本分句
    sentences = sent_tokenize(text)

    # 获取英文停用词列表
    stop_words = set(stopwords.words('english'))

    for sentence in sentences:
        # 2. 单词分词
        words = word_tokenize(sentence)

        # 3. 移除停用词和非字母数字字符（可选，但有助于清洗）
        filtered_words = [
            word for word in words 
            if word.isalpha() and word.lower() not in stop_words
        ]

        # 4. 词性标注
        # nltk.pos_tag 返回一个元组列表，例如 [('word', 'POS_TAG')]
        tagged_words = nltk.pos_tag(filtered_words)

        # 5. 名词筛选
        # 识别以 'NN' 开头的标签（NN, NNS, NNP, NNPS）
        for word, tag in tagged_words:
            if tag.startswith('NN'):
                extracted_nouns.append(word)

    return extracted_nouns

# 示例文本，可以替换为你的 LLM 响应或其他任何文本
sample_text = """
The quick brown fox jumps over the lazy dog. John went to Paris, the capital of France.
Artificial intelligence is transforming many industries, creating new opportunities and challenges.
Companies like Google and Microsoft are investing heavily in AI research.
"""

# 提取名词并打印
nouns = extract_nouns(sample_text)
print(f"原始文本:\n{sample_text}\n")
print(f"提取到的名词: {nouns}")

# 另一个示例
response_message = "I have a task that involves extracting nouns from a variable called message: response. I want to display the extracted nouns in the console or print them on the screen. How can I accomplish this task using Python? I have tried using some libraries like NLTK and TextBlob, but I am not sure how to use them correctly. I have also asked GitHub Copilot for help, but it did not generate any useful code. It just showed me some random output that did not work."
nouns_from_response = extract_nouns(response_message)
print(f"\nLLM响应示例:\n{response_message}\n")
print(f"从LLM响应中提取到的名词: {nouns_from_response}")

提取到的名词: ['fox', 'dog', 'John', 'Paris', 'capital', 'France', 'intelligence', 'industries', 'opportunities', 'challenges', 'Companies', 'Google', 'Microsoft', 'AI', 'research']