如何在Python中对GENIA语料库进行XML解析

import xml.etree.ElementTree as ET

# 加载GENIA语料库XML文件
tree = ET.parse('genia_corpus.xml')
root = tree.getroot()

# 遍历XML文件中的每个句子
for sentence in root.iter('sentence'):
    # 获取句子的ID
    sentence_id = sentence.attrib['id']
    print(f"Sentence ID: {sentence_id}")

    # 遍历句子中的每个单词
    for word in sentence.iter('word'):
        # 获取单词的文本和词性标记
        word_text = word.text
        word_pos = word.attrib['pos']
        print(f"Word: {word_text}, POS: {word_pos}")

    print()  # 打印空行分隔每个句子