Designing the backbone of the RHDT using AI and Network Science
This resource discusses how the ARTEMIS project combines artificial intelligence, network science, knowledge graphs, and semantic ontologies to transform unstructured cultural heritage data into structured, machine-readable knowledge supporting Reactive Heritage Digital Twins (RHDTs). The presentation explores how technologies such as Natural Language Processing (NLP), Computer Vision, embeddings, and large language models (LLMs) help extract, interpret, and connect information from heterogeneous sources. Particular emphasis is placed on the semi-automatic construction of semantic knowledge structures, highlighting the importance of open-source AI, scalability, and expert human validation in creating reliable and collaborative cultural heritage infrastructure within ARTEMIS.
Learning Outcomes
After completing this module, learners will be able to:
- identify the main components of a knowledge graph.
- summarize how large language models (LLMs) and computer vision support the transformation of unstructured data into structured knowledge graphs.
- differentiate between human contextual understanding and machine interpretation of multimodal data.
- examine how embeddings enable similarity detection across textual and visual representations.
