Learning Pattern-Based Extractors from Natural Language and Knowledge Graphs Applying Large Language Models to Wikipedia & the Linked Open Data (POSTER)

Celian Ringwald (1, 2) , Fabien Gandon (1, 3) , Catherine Faron (2, 4, 1) , Franck Michel (3, 1) , Hanna Abi Akl (1, 5)

1 WIMMICS - Web-Instrumented Man-Machine Interactions, Communities and Semantics
2 UniCA - Université Côte d'Azur
3 Laboratoire I3S - SPARKS - Scalable and Pervasive softwARe and Knowledge Systems
4 I3S - Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis
5 DSTI Labs - Data ScienceTech Institute

Seq-to-seq transformer models have recently been successfully used for relation extraction, showing their flexibility, effectiveness and scalability on that task. In this context, knowledge graphs coupled with Wikipedia (e.g. DBpedia, Wikidata) allow us to leverage existing texts and corresponding RDF graphs to learn to extract such knowledge from text. The goal of this work is to learn efficient targeted extractors for specific RDF patterns by leveraging the latest language models and the dual base formed by Wikipedia on the one hand, and DBpedia & Wikidata on the other hand.

Keywords: Semantic Web; Knowlede Graph; NLP

Domains: Document and Text Processing; Databases [cs.DB]; Web; Machine Learning [stat.ML]

Celian Ringwald, Fabien Gandon, Catherine Faron, Franck Michel, Hanna Abi Akl. Learning Pattern-Based Extractors from Natural Language and Knowledge Graphs Applying Large Language Models to Wikipedia & the Linked Open Data (POSTER). AAAI 2024 - 38th Annual AAAI Conference on Artificial Intelligence, Feb 2024, Vancouver, France. . ⟨hal-04526139⟩