WorldKG: World-Scale Completion of Geographic Knowledge

OpenStreetMap （OSM）是一个丰富的公开可用的自愿地理信息来源。OSM被网络上的各种实际应用所采用，包括在线路线规划器和地理信息站点。然而，OSM中地理实体的表示是高度多样化和不完整的，受限于少数强制属性和异构标记，即用户定义的键值对。最近出现的知识图（即基于图的知识库），如Wikidata、EventKG和DBpedia，提供了丰富的地理实体上下文信息来源，并支持语义查询。例如，2018年9月，维基数据包含超过640万个实体，包括地点、兴趣点、山峰等。虽然知识图为地理实体提供了广泛的互补语义信息，对Web应用程序非常有用，但OSM和知识图之间的身份链接仍然很少，并且主要由志愿者手动定义。由于OSM数据集的大规模、丰富性、异质性和不同的定位，链路发现问题尤其具有挑战性。WordKG项目的主要目标是促进世界范围内用知识图连接描述不同地理区域的OSM数据集，并利用OSM数据完成知识图中的空间知识。这一目标可以转化为三个主要目标：1)在模式和实例级别开发用于OSM数据集和知识图的世界范围对齐的方法。2)开发了基于VGI的知识图谱的实例融合完成方法，并基于VGI信息创建新的语义实例。3)将这些方法得到的数据以WorldKG知识图谱的形式进行准备和发布，该知识图谱提供了地理信息及其上下文的综合语义表示。WorldKG项目的成果可以极大地促进移动、交通、旅游和物流领域的应用，并通过高质量的地理和上下文信息语义表示为信息地图和服务提供基础。

OpenStreetMap (OSM) is a rich source of openly available volunteered geographic information. OSM is adopted by a variety of real-world applications on the Web and beyond, including online route planners and geographic information sites. However, representations of geographic entities in OSM are highly diverse and incomplete, being restricted to few mandatory properties and heterogeneous tags, i.e. user-defined key-value pairs.Recently emerged knowledge graphs (i.e. graph-based knowledge repositories) such as Wikidata, EventKG and DBpedia provide a rich source of contextual information about geographic entities and support semantic queries. For example, in September 2018 Wikidata contained more than 6.4 million entities including locations, points of interest, mountain peaks and others.Whereas knowledge graphs provide a wide range of complementary semantic information for geographic entities, highly useful for Web applications, identity links between OSM and knowledge graphs are still rare and are mainly manually defined by volunteers.The problem of link discovery for OSM datasets is particularly challenging due to the large scale, richness, heterogeneity and different localisation.The main goal of the WordKG project is to facilitate world-scale interlinking of OSM datasets describing different geographic regions with knowledge graphs as well as completion of spatial knowledge in the knowledge graphs using OSM data.This goal is translated into three main objectives:1) Development of methods for world-scale alignment of OSM datasets and knowledge graphs at the schema and instance level.2) Development of methods for VGI-based knowledge graph completion through instance fusion and creation of new semantic instances based on VGI information.3 ) Preparation and release data resulting from these methods in form of the WorldKG knowledge graph that provides comprehensive semantic representation of geographical information and its context.The results of the WorldKG project can substantially benefit applications in mobility, transportation, tourism and logistics domains, as well as provide a basis for informational maps and services through high quality semantic representation of geographical and contextual information.