如何使用Spacy的转换来保存conllu文件中的段落信息？

pip install spacy
python -m spacy download en

import spacy

nlp = spacy.load('en')

with open('example.conllu', 'r', encoding='utf-8') as file:
    text = file.read()

doc = nlp(text)

paragraphs = []
current_paragraph = []
for sent in doc.sents:
    if len(sent) == 0:  # 空行表示段落分隔
        if current_paragraph:
            paragraphs.append(current_paragraph)
            current_paragraph = []
    else:
        current_paragraph.append(sent)

# 添加最后一个段落
if current_paragraph:
    paragraphs.append(current_paragraph)

with open('output.conllu', 'w', encoding='utf-8') as file:
    for i, paragraph in enumerate(paragraphs):
        file.write(f'# Paragraph {i+1}\n')
        for sent in paragraph:
            file.write(sent.text)
            file.write('\n')
        file.write('\n')