Geolocation of Cultural Heritage using Multi-View Knowledge Graph Embedding
This addresses the challenge of missing geolocation attributes for cultural heritage entities like sculptures and paintings, which is incremental as it builds on existing knowledge graph methods.
The paper tackles the problem of incomplete geographical location data in cultural heritage knowledge graphs by proposing a framework for ingesting multi-hop knowledge and a multi-view learning model to estimate relative distances between entities, achieving unspecified results.
Knowledge Graphs (KGs) have proven to be a reliable way of structuring data. They can provide a rich source of contextual information about cultural heritage collections. However, cultural heritage KGs are far from being complete. They are often missing important attributes such as geographical location, especially for sculptures and mobile or indoor entities such as paintings. In this paper, we first present a framework for ingesting knowledge about tangible cultural heritage entities from various data sources and their connected multi-hop knowledge into a geolocalized KG. Secondly, we propose a multi-view learning model for estimating the relative distance between a given pair of cultural heritage entities, based on the geographical as well as the knowledge connections of the entities.