Generating Explainable Abstractions for Wikidata Entities

The large coverage and quality of the Wikidata knowledge graph make it suitable for usage in downstream applications, such as entity summarization, entity linking, and question answering. Yet, most retrieval and similarity-based methods for Wikidata make limited use of its semantics, and lose the link between the rich structure in Wikidata and the decision-making algorithm. In this paper, we investigate how to define abstractive representations (profiles) of Wikidata entities. We propose a scalable method that can produce profiles for Wikidata entities based on salient labels associated with their types. We represent the resulting profiles as a graph, and compute profile embeddings. Our empirical analysis shows that the profiles can capture similarity competitively to baselines, but excel in terms of explainability. On the task of neural entity linking in tables, the profiles outperform all baselines in terms of accuracy, whereas their human-readable representation clearly explains the source of improvement. We make our code and data available to facilitate novel use cases based on the Wikidata profiles.