Communication Dans Un Congrès Année : 2024

Streamlining Event Relation Extraction: A Pipeline Leveraging Pretrained and Large Language Models for Inference

Gustavo Flores Miguel
  • Fonction : Auteur
  • PersonId : 1556925
Youssra Rebboud
Pasquale Lisena
Raphäel Troncy

Résumé

Event relation extraction is crucial for understanding the temporal sequence and interconnections between events. To demonstrate this, we developed a Streamlit-based application that showcases our event relation extraction system, capable of identifying semantically accurate relations such as Direct-cause, Enable, Intend, and Prevent. The system features an API that simplifies inference and displays results in a user-friendly manner. Users can input text like a sentence and the application highlights extracted events and their corresponding relationships. The backend runs a series of pre-trained language models, trained on datasets focused on events and their semantic relations. The app allows users to switch between various models, including HuggingFace's RoBERTa, REBEL, and large language models like Zephyr. The demo is available at https://demo.kflow.eurecom.fr/.

Fichier principal
Vignette du fichier
PD_paper_184.pdf (717.2 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05135516 , version 1 (30-06-2025)

Licence

Identifiants

  • HAL Id : hal-05135516 , version 1

Citer

Gustavo Flores Miguel, Youssra Rebboud, Pasquale Lisena, Raphäel Troncy. Streamlining Event Relation Extraction: A Pipeline Leveraging Pretrained and Large Language Models for Inference. EKAW 2024, 24th International Conference on Knowledge Engineering and Knowledge Management, Poster and Demo Track, CEUR, Nov 2024, Amsterdam, Netherlands. ⟨hal-05135516⟩

Collections

170 Consultations
241 Téléchargements

Partager

  • More