PLSUM：通过汇总多个网站生成PT-BR维基百科
PLSUM: Generating PT-BR Wikipedia by Summarizing Multiple Websites
摘要：
维基百科是一个重要的免费知识来源。尽管如此，巴西葡萄牙语维基百科仍然缺乏对许多主题的描述。为了扩大巴西维基百科，我们贡献了PLSum，一个从多个描述性网站生成类似维基的摘要的框架。该框架有一个提取阶段，随后是一个抽象阶段。特别是，对于抽象阶段，我们微调和比较了Transformer神经网络的两个最新版本PTT5和Longformer。为了微调和评估模型，我们创建了一个包含数千个示例的数据集，将参考网站链接到维基百科。我们的研究结果表明，它是可能的巴西葡萄牙语的网页内容生成有意义的摘要。
英文摘要：
Wikipedia is an important free source of intelligible knowledge. Despite that, Brazilian Portuguese Wikipedia still lacks descriptions for many subjects. In an effort to expand the Brazilian Wikipedia, we contribute PLSum, a framework for generating wiki-like abstractive summaries from multiple descriptive websites. The framework has an extractive stage followed by an abstractive one. In particular, for the abstractive stage, we fine-tune and compare two recent variations of the Transformer neural network, PTT5, and Longformer. To fine-tune and evaluate the model, we created a dataset with thousands of examples, linking reference websites to Wikipedia. Our results show that it is possible to generate meaningful abstractive summaries from Brazilian Portuguese web content.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
