我们认为，“使用知识库的问答系统”和"通过关联数据的问答系统“目前是同一个问题的两个实例，尽管其中一个明确说明要处理关联数据。在论文中，我们指出了现有的方法无法对：（1）利用外部链接到云服务器中使用其他数据集的问答系统；（2）利用共享公共数据集的问答系统进行评估。为此，我们提议创建新的评估设定，以利用语义网的优势来实现人工智能完备（AI-complete）的问答系统。

原文题目：Where is Linked Data in Question Answering over Linked Data?

原文：We argue that "Question Answering with Knowledge Base" and "Question Answering over Linked Data" are currently two instances of the same problem, despite one explicitly declares to deal with Linked Data. We point out the lack of existing methods to evaluate question answering on datasets which exploit external links to the rest of the cloud or share common schema. To this end, we propose the creation of new evaluation settings to leverage the advantages of the Semantic Web to achieve AI-complete question answering.

原文作者：Tommaso Soru, Edgard Marx, André Valdestilhas, Diego Moussallem, Gustavo Publio, Muhammad Saleem

原文地址：https://arxiv.org/abs/2005.03640