Prompt-based Data Augmentation for Semantically-Precise Event Relation Classification - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Prompt-based Data Augmentation for Semantically-Precise Event Relation Classification

Résumé

The process of recognizing and classifying the relationships between events mentioned in the text is a crucial task in natural language processing (NLP) known as event relation extraction. If temporal relations and causality are largely studied in the literature, other types of relations have found less interest. Our study specifically concentrates on four types of event relations: causality, enabling, prevention, and intention. Our main contribution consists of the use of a state-of-the-art language model (GPT-3) to extend an existing small dataset with synthetic examples to address the challenge of insufficient training data. We evaluate the quality of these generated samples by training an event relations extraction system, showing improved performances in classifying event relations.
Fichier principal
Vignette du fichier
publi-7298.pdf (253.82 Ko) Télécharger le fichier
publi-7298 (1).pdf (253.82 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04121015 , version 1 (07-06-2023)

Identifiants

  • HAL Id : hal-04121015 , version 1

Citer

Youssra Rebboud, Pasquale Lisena, Raphaël Troncy. Prompt-based Data Augmentation for Semantically-Precise Event Relation Classification. SEMMES 2023, CEUR, May 2023, Heraklion, Greece. ⟨hal-04121015⟩

Collections

EURECOM ANR
37 Consultations
47 Téléchargements

Partager

Gmail Facebook X LinkedIn More