DBkWik++ -- Multi Source Matching of Knowledge Graphs

TL;DR

This paper introduces DBkWik++, a large, fused knowledge graph created by merging thousands of wiki-based knowledge graphs, enhancing coverage of long-tail entities through a multi-source matching approach.

Contribution

It presents a novel multi-source knowledge graph matching method that leverages existing one-to-one systems to fuse numerous wiki-based graphs into a comprehensive resource.

Findings

Created a knowledge graph with over 15 million instances.

Demonstrated effective multi-source merging of wiki-based knowledge graphs.

Extended coverage to long-tail entities beyond traditional sources.

Abstract

Large knowledge graphs like DBpedia and YAGO are always based on the same source, i.e., Wikipedia. But there are more wikis that contain information about long-tail entities such as wiki hosting platforms like Fandom. In this paper, we present the approach and analysis of DBkWik++, a fused Knowledge Graph from thousands of wikis. A modified version of the DBpedia framework is applied to each wiki which results in many isolated Knowledge Graphs. With an incremental merge based approach, we reuse one-to-one matching systems to solve the multi source KG matching task. Based on this alignment we create a consolidated knowledge graph with more than 15 million instances.