KGvec2go – Knowledge Graph Embeddings as a Service

Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), pages 5641–5647 Marseille, 11–16 May 2020 c⃝ European Language Resources Association (ELRA), licensed under CC-BY-NC 5641 KGvec2go – Knowledge Graph Embeddings as a Service Jan Portisch (1,2), Michael Hladik (2), Heiko Paulheim (1) (1) University of Mannheim - Data and Web Science Group, (2) SAP SE (1) B 6, 26 68159 Mannheim, Germany (2) Dietmar-Hopp Allee 16, 60190, Walldorf, Germany jan@informatik.uni-mannheim.de, michael.hladik@sap.com, heiko@informatik.uni-mannheim.de Abstract In this paper, we present KGvec2go, a Web API for accessing and consuming graph embeddings in a light-weight fashion in downstream applications. Currently, we serve pre-trained embeddings for four knowledge graphs. We introduce the service and its usage, and we show further that the trained models have semantic value by evaluating them on multiple semantic benchmarks. The evaluation also reveals that the combination of multiple models can lead to a better outcome than the best individual model. Keywords: RDF2Vec, knowledge graph embeddings, knowledge graphs, background knowledge resources 1. Introduction A knowledge graph (KG) stores factual information in the form of triples. Today, many such graphs exist for various domains, are publicly available, and are being interlinked. As of 2019, the linked open data cloud (Schmachtenberg et al., 2014) counts more than 1,000 data sets with multiple billions of unique triples.1 Knowledge graphs are typically consumed using factual queries for downstream tasks such as question answering. Recently, knowledge graph embed- ding models are explored as a new way of knowledge graph exploitation. KG embeddings (KGEs) represent nodes and (depending on the approach) also edges as continuous vec- tors. One such approach is RDF2Vec (Ristoski and Paul- heim, 2016). It has been used and evaluated for machine learning, entity and document modeling, and for recom- mender systems (Ristoski et al., 2019). RDF2Vec vectors trained on a large knowledge graph have also been used as background knowledge source for ontology matching (Por- tisch and Paulheim, 2018). While it has been shown that KGEs are helpful in many ap- plications, embeddings on larger knowledge graphs can be expensive to train and to use for downstream applications. kgvec2go.org, therefore, allows to easily access and consume concept embeddings through simple Web APIs. Since most downstream applications only require embed- ding vectors for a small subset of all concepts, computing a complete embedding model or downloading a complete pre-computed one is often not desirable. With KGvec2go, rather than having to download the com- plete embedding model, a Web query can be used to ob- tain only the desired concept in vector representation or even a derived statistic such as the similarity between two concepts. This facilitates downstream applications on less powerful devices, such as smartphones, as well as the appli- cation of knowledge graph embeddings in machine learning scenarios where the data scientists do not want to train the models themselves or do not have the means to perform the computations. Models for four knowledge graphs were learned, namely: DBpedia (Lehmann et al., 2015), WebIsALOD (Hertling and Paulheim, 2017), Wiktionary (S´erasset, …

Content truncated to 500 words