Building Knowledge Graphs
Talkat Open Source Summit Europe 2023 · on Thursday, 2023-09-21· at 12:50· Room 0D-2-0D-3 (Floor 0), Abandoibarra Etorb., 4, 48011 Bilbao, Bizkaia, Spain·
summary
Knowledge graphs require a graph database plus shared ontologies and taxonomies, not just one-off engineering, and work best when domain experts, data engineers and modelers collaborate. RDF gives inferencing via subject‑predicate‑object triples and SHACL validation; labeled property graphs give fast graph analytics; queries use SPARQL and SHACL and tools like Protegé and R2R for mapping. Expect ~75–80% unstructured data to be extracted, Ontotext’s GraphDB is benchmarked for scale, and KGs pair with LLMs to reduce hallucination and validate outputs.
AI-written summary · about
chapters (8)
- 0:00Building knowledge graphs
- 10:25Graph vs knowledge graphs
- 17:28Ontologies and taxonomies
- 24:28Taxonomy standards
- 31:11Ontologies as schemas
- 35:46Building steps
- 39:00Implementation guidelines
- 40:52Q&A
related talks
44mBuilding Knowledge Graphs
46mBuilding Knowledge Graphs
24mWhy You Need a Knowledge Graph And How to Build It
21mMastering Knowledge Graph Transformations Without Compromising Meaning
30mGraph Data Science
22mThe Nexus of Innovation: How Knowledge Graphs Fuel AI Scientific Breakthroughs
33mSmarter Industrial Fault Diagnosis with Knowledge Graphs and Large Language Models
30mEntity Resolved Knowledge Graphs