MUSEKG: A Knowledge Graph Over Museum Collections
This addresses the challenge of creating coherent and queryable systems for cultural heritage institutions, enabling better integration and reasoning over digital museum collections.
The paper tackles the problem of integrating fragmented and heterogeneous museum data by introducing MuseKG, an end-to-end knowledge graph framework that unifies structured and unstructured data through symbolic-neural integration, demonstrating robust performance in queries over real museum collections and surpassing baselines like large-language-model zero-shot and SPARQL prompts.
Digital transformation in the cultural heritage sector has produced vast yet fragmented collections of artefact data. Existing frameworks for museum information systems struggle to integrate heterogeneous metadata, unstructured documents, and multimodal artefacts into a coherent and queryable form. We present MuseKG, an end-to-end knowledge-graph framework that unifies structured and unstructured museum data through symbolic-neural integration. MuseKG constructs a typed property graph linking objects, people, organisations, and visual or textual labels, and supports natural language queries. Evaluations on real museum collections demonstrate robust performance across queries over attributes, relations, and related entities, surpassing large-language-model zero-shot, few-shot and SPARQL prompt baselines. The results highlight the importance of symbolic grounding for interpretable and scalable cultural heritage reasoning, and pave the way for web-scale integration of digital heritage knowledge.