Well-Written Knowledge Graphs: Most Effective RDF Syntaxes for Triple Linearization in End-to-End Extraction of Relations from Texts (Student Abstract)

Seq-to-seq generative models recently gained attention for solving the relation extraction task. By approaching this problem as an end-to-end task, they surpassed encoder-based-only models. Little research investigated the effects of the output syntaxes on the training process of these models. Moreover, a limited number of approaches were proposed for extracting ready-to-load knowledge graphs following the RDF standard. In this paper, we consider that a set of triples can be linearized in many different ways, and we evaluate the combined effect of the size of the language models and different RDF syntaxes on the task of relation extraction from Wikipedia abstracts.

Authors

• Célian Ringwald Université Côte d’Azur, Inria, CNRS, I3S
• Fabien Gandon Université Côte d’Azur, Inria, CNRS, I3S Data ScienceTech Institute
• Catherine Faron Université Côte d’Azur, Inria, CNRS, I3S
• Franck Michel Université Côte d’Azur, Inria, CNRS, I3S
• Hanna Abi Akl Université Côte d’Azur, Inria, CNRS, I3S Data ScienceTech Institute

Keywords

• DMKM: Knowledge Acquisition From The Web
• DMKM: Linked Open Data Knowledge Graphs & KB Completion
• NLP: Information Extraction
• NLP: Large Language Models