Research on link prediction in knowledge graphs has mainly focused on static multirelational data. In this work we consider temporal knowledge graphs where relations between entities may only hold for a time interval or a specific point in time. In line with previous work on static knowledge graphs, we propose to address this problem by learning latent entity and relation type representations. To incorporate temporal information, we utilize recurrent neural networks to learn timeaware representations of relation types which can be used in conjunction with existing latent factorization methods. The proposed approach is shown to be robust to common challenges in real-world KGs: the sparsity and heterogeneity of temporal expressions. Experiments show the benefits of our approach on four temporal KGs.

While the realization of the Semantic Web as once envisioned by Tim Berners-Lee remains in a distant future, the Web of Data has already become a reality. Billions of RDF statements on the Internet, facts about a variety of different domains, are ready to be used by semantic applications. Some of these applications, however, crucially hinge on the availability of expressive schemas suitable for logical inference that yields non-trivial conclusions. In this paper, we present a statistical approach to the induction of expressive schemas from large RDF repositories. We describe in detail the implementation of this approach and report on an evaluation that we conducted using several data sets including DBpedia.

We present MMKG, a collection of three knowledge graphs that contain both numerical features and (links to) images for all entities as well as entity alignments between pairs of KGs. Therefore, multi-relational link prediction and entity matching communities can benefit from this resource. We believe this data set has the potential to facilitate the development of novel multi-modal learning approaches for knowledge graphs. We validate the utility of MMKG in the sameAs link prediction task with an extensive set of experiments. These experiments show that the task at hand benefits from learning of multiple feature types.

Abstract. It has been argued that linked open data is the major benefit of semantic technologies for the web as it provides a huge amount of structured data that can be accessed in a more effective way than web pages. While linked open data avoids many problems connected with the use of expressive ontologies such as the knowledge acquisition bottleneck, data heterogeneity remains a challenging problem. In particular, identical objects may be referred to by different URIs in different data sets. Identifying such representations of the same object is called object reconciliation. In this paper, we propose a novel approach to object reconciliation that is based on an existing semantic similarity measure for linked data. We adapt the measure to the object reconciliation problem, present exact and approximate algorithms that efficiently implement the methods, and provide a systematic experimental evaluation based on a benchmark dataset. As our main result, we show that the use of lightweight ontologies and schema information significantly improves object reconciliation in the context of linked open data.

No abstract