Assisted Knowledge Graph Authoring: Human-Supervised Knowledge Graph Construction from Natural Language
This addresses the need for domain experts in fields like history, physics, or medicine to build custom knowledge graphs more easily, though it appears incremental as it builds on existing knowledge graph construction methods.
The paper tackles the problem of underrepresentation of domain-specific knowledge in existing knowledge graphs by introducing WAKA, a web application that enables domain experts to construct knowledge graphs using natural language, facilitating the creation of specialized retrieval applications.
Encyclopedic knowledge graphs, such as Wikidata, host an extensive repository of millions of knowledge statements. However, domain-specific knowledge from fields such as history, physics, or medicine is significantly underrepresented in those graphs. Although few domain-specific knowledge graphs exist (e.g., Pubmed for medicine), developing specialized retrieval applications for many domains still requires constructing knowledge graphs from scratch. To facilitate knowledge graph construction, we introduce WAKA: a Web application that allows domain experts to create knowledge graphs through the medium with which they are most familiar: natural language.