Universal Preprocessing Operators for Embedding Knowledge Graphs with Literals
This addresses the challenge of integrating multiple literal modalities in KGs for researchers and practitioners, though it is incremental as it builds on existing embedding techniques.
The paper tackles the problem of embedding knowledge graphs with diverse literal values by proposing universal preprocessing operators that transform KGs for use with any embedding method, achieving promising results on the kgbench dataset with three methods.
Knowledge graph embeddings are dense numerical representations of entities in a knowledge graph (KG). While the majority of approaches concentrate only on relational information, i.e., relations between entities, fewer approaches exist which also take information about literal values (e.g., textual descriptions or numerical information) into account. Those which exist are typically tailored towards a particular modality of literal and a particular embedding method. In this paper, we propose a set of universal preprocessing operators which can be used to transform KGs with literals for numerical, temporal, textual, and image information, so that the transformed KGs can be embedded with any method. The results on the kgbench dataset with three different embedding methods show promising results.