Se ha denunciado esta presentación.
Utilizamos tu perfil de LinkedIn y tus datos de actividad para personalizar los anuncios y mostrarte publicidad más relevante. Puedes cambiar tus preferencias de publicidad en cualquier momento.

Building a Knowledge Graph using NLP and Ontologies

229 visualizaciones

Publicado el

Speakers: Jesús Barrasa, EMEA Sales Engineering Director, Neo4j

Mark Needham, Developer Relations Engineer, Neo4j

Publicado en: Tecnología
  • Inicia sesión para ver los comentarios

Building a Knowledge Graph using NLP and Ontologies

  1. 1. Building a Knowledge Graph using NLP and Ontologies Jesús Barrasa - EMEA Sales Engineering Director Mark Needham - Developer Relations Engineer
  2. 2. 2 Knowledge Graph: Knowledge + Facts Facts Explicit Knowledge
  3. 3. 3 Knowledge Graph: Knowledge + Facts instance data explicit description of how instance data relates Facts Explicit Knowledge
  4. 4. 4 Knowledge Graph: Knowledge + Facts Graph data imported from any data source Structured: relational, file, hierarchical JSON/XML Semistructured: HTML, documents, Facts come from (public) ontologies, taxonomies or any kind of metadata definition Explicit Knowledge
  5. 5. • Software taxonomies from Wikidata • Technical articles from dev.to • Entity Extraction using GCP's NLP API • Software Stacks Ontology (OWL) 5 Software knowledge graph
  6. 6. • Semantic search • Item similarity • Inference • Detect inconsistencies 6 What can we do with knowledge graphs?
  7. 7. • Semantic search • Item similarity • Inference • Detect inconsistencies 7 What can we do with knowledge graphs?
  8. 8. • Wikidata SPARQL API • neosemantics (n10s) • APOC 8 Tools used in this talk
  9. 9. Wikidata is a free and open knowledge base that can be read and edited by both humans and machines. Wikidata acts as central storage for the structured data of its Wikimedia sister projects including Wikipedia, Wikivoyage, Wiktionary, Wikisource, and others. 9 Wikidata
  10. 10. neosemantics is a plugin that enables the use of RDF in Neo4j • Store RDF data in Neo4j in a lossless manner • On-demand export property graph data from Neo4j as RDF • Model mapping • Constraint Validation and Inferencing 10 neosemantics (n10s)
  11. 11. APOC is Neo4j's standard utility library. It includes over 450 standard procedures, providing functionality for utilities, conversions, graph updates, and more. 11 APOC
  12. 12. APOC is Neo4j's standard utility library. It includes over 450 standard procedures, providing functionality for utilities, conversions, graph updates, and more. 12 APOC
  13. 13. • Importing Wikidata using n10s • Scraping technical articles from dev.to • Entity extraction using GCP NLP API • Querying the knowledge graph 13 Demo structure
  14. 14. 2. Scraping technical articles from dev.to 14 Demo structure Facts Explicit Knowledge 1. Importing Wikidata using n10s 3. Entity extraction using GCP NLP API

×