Before the research papers. Before the architecture arguments. There are the objects th...

Before the research papers. Before the architecture arguments. There are the objects themselves.

The Edward Monk YouTube channel has been quietly publishing narrated descriptions of public domain museum objects from the LinkedCulture collection. Over 100 so far. Each image described by AI and combined with their metadata to create a new narrative, written to be genuinely useful for someone who cannot see the image.

Every object is CC0 licensed. Every description is free to share.

This is what LinkedCulture is actually for. Not the infrastructure, not the retrieval architecture...the objects. The photograph that exists in a collection somewhere and the person who needed to find it. This is one more example of how collections can reach the public.

The research series launching on the same channel goes deeper on why discovery fails and what a layered architecture does differently. But the videos are one way it all becomes concrete.

Watch the shorts: https://lnkd.in/eJPNhZDt

Explore the collection: https://linkedculture.org/ The research behind this series is documented in several papers: Paper 1: Discovery architecture for cultural heritage: layered retrieval, institutional authority, and the limits of keyword search https://linkedculture.org/research/discovery-architecture-for-cultural-heritage

Paper 2: Discovery architecture for cultural heritage: layered retrieval, institutional authority, and the limits of keyword search https://linkedculture.org/research/embedding-cultural-heritage-metadata

Paper 3: Semantic Clusters and Language Partitioning in a Multi-Institutional Cultural Heritage Index https://linkedculture.org/research/semantic-clusters-language-partitioning

Learn more about LinkedCulture and the work behind it: https://linkedculture.org/