The Semantic Web movement has produced a wealth of curated collections of entities and facts, often referred as Knowledge Graphs. Creating and maintaining such Knowledge Graphs is far from being a solved problem: it is crucial to constantly extract new information from the vast amount of heterogeneous sources of data on the Web. In this work we address the task of Knowledge Graph population. Specifically, given any target relation between two entities, we propose an approach to extract positive instances of the relation from various Web sources. Our relation extraction approach introduces a human-in-the-loop component in the extraction pipeline, which delivers significant advantage with respect to other solely automatic approaches. We test our solution on the ISWC 2018 Semantic Web Challenge, with the objective to identify supply-chain relations among organizations in the Thomson Reuters Knowledge Graph. Our human-in-the-loop extraction pipeline achieves top performance among all competing systems.

语义网运动产生了大量精选的实体和事实集合，通常被称为知识图。创建和维护这样的知识图谱还远不是一个解决的问题：至关重要的是不断从Web上大量的异构数据源中提取新信息。在这项工作中，我们解决了知识图填充的任务。具体来说，给定两个实体之间的任何目标关系，我们提出了一种从各种Web源中提取关系的肯定实例的方法。我们的关系提取方法在提取管道中引入了“人在回路”的组件，相对于其他完全自动化的方法，它具有明显的优势。我们在ISWC 2018语义网挑战赛上测试了我们的解决方案，目的是在汤姆森路透知识图谱中确定组织之间的供应链关系。我们的人在回路提取管道可在所有竞争系统中实现最高性能。