POPCORN: Fictional and Synthetic Intelligence Reports for Named Entity Recognition and Relation Extraction Tasks - GETALP
Communication Dans Un Congrès Année : 2024

POPCORN: Fictional and Synthetic Intelligence Reports for Named Entity Recognition and Relation Extraction Tasks

Résumé

POPCORN is a research project aiming at maturing Information Extraction (IE) solutions for intelligence services. Due to defense security constraints, reports analyzed by intelligence services are not to be accessible to the scientific community. To address this challenge, we propose a dataset made of "fictional" (handcrafted) and "synthetic" (AI generated) French reports. Those synthetic reports are produced by an innovative approach that generates texts closely resembling real-world intelligence reports, facilitating the training and evaluation of IE tasks such as Entity and Relation Extraction. Experiments demonstrate the interest of synthetic reports to enhance the performance of IE models, showcasing their potential to augment real-world intelligence operations.
Fichier principal
Vignette du fichier
KES_2024.pdf (300.47 Ko) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-04708175 , version 1 (24-09-2024)

Identifiants

  • HAL Id : hal-04708175 , version 1

Citer

Bastien Giordano, Maxime Prieur, Maxime Prieur, Nakanyseth Vuth, Sylvain Verdy, et al.. POPCORN: Fictional and Synthetic Intelligence Reports for Named Entity Recognition and Relation Extraction Tasks. 28th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES 2024), Sep 2024, Seville, Spain. ⟨hal-04708175⟩
23 Consultations
17 Téléchargements

Partager

More