Towards Ontologically Grounded and Language-Agnostic Knowledge Graphs
This addresses a major problem for applications like recommendation engines and search systems that rely on knowledge graphs, though it appears incremental as it builds on existing ontological distinctions.
The paper tackles the challenge of updating and integrating knowledge graphs across domains and languages by proposing an ontologically grounded and language-gnostic representation, which reifies abstract objects and distinguishes concepts from types to alleviate integration difficulties.
Knowledge graphs (KGs) have become the standard technology for the representation of factual information in applications such as recommendation engines, search, and question-answering systems. However, the continual updating of KGs, as well as the integration of KGs from different domains and KGs in different languages, remains to be a major challenge. What we suggest here is that by a reification of abstract objects and by acknowledging the ontological distinction between concepts and types, we arrive at an ontologically grounded and language-agnostic representation that can alleviate the difficulties in KG integration.