使用nltk恢复原始单词，并使用完整语义进行标记化

import nltk
from nltk.stem import WordNetLemmatizer

def restore_original_words(text):
    lemmatizer = WordNetLemmatizer()
    tokens = nltk.word_tokenize(text)
    restored_words = []
    for token in tokens:
        restored_word = lemmatizer.lemmatize(token)
        restored_words.append(restored_word)
    return ' '.join(restored_words)

def mark_with_complete_semantics(text):
    tagged_words = nltk.pos_tag(nltk.word_tokenize(text))
    return tagged_words

# 示例文本
text = "I am running in the park"

# 恢复原始单词
restored_text = restore_original_words(text)
print(restored_text)
# 输出: "I am running in the park"

# 使用完整语义进行标记化
tagged_text = mark_with_complete_semantics(restored_text)
print(tagged_text)
# 输出: [('I', 'PRP'), ('am', 'VBP'), ('running', 'VBG'), ('in', 'IN'), ('the', 'DT'), ('park', 'NN')]