Well-written Knowledge Graphs Most Effective RDF Syntaxes for Triple Linearization in End-to-End Extraction of Relations from Text (Student Abstract)
Résumé
Large generative language models recently gained attention for solving relation extraction tasks, notably because of their flexibility. This is in contrast to encoder-only models that require the definition of predefined output patterns. There has been little research into the impact of the syntax chosen to represent a graph as a sequence of tokens. Moreover, a few approaches have been proposed to extract ready-to-load knowledge graphs following the RDF standard. In this paper, we consider that a set of RDF triples can be linearized in many ways and we evaluate the combined impact of language model size as well as different RDF syntaxes on the task of relation extraction from Wikipedia abstracts
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|---|
| Licence |
![]()
Est décrite par hal-04384724 Objet présenté à une conférence Célian Ringwald, Fabien Gandon, Catherine Faron, Franck Michel, Hanna Abi Akl. Well-Written Knowledge Graphs: Most Effective RDF Syntaxes for Triple Linearization in End-to-End Extraction of Relations from Texts (Student Abstract). AAAI 2024 - 38th Annual AAAI Conference on Artificial Intelligence, Association for the Advancement of Artificial Intelligence, Feb 2024, Vancouver, Canada. pp.23631-23632, ⟨10.1609/aaai.v38i21.30502⟩. ⟨hal-04384724⟩