Beyond Model Performance: Can Link Prediction Enrich French Lexical Graphs? - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

Beyond Model Performance: Can Link Prediction Enrich French Lexical Graphs?

Au-delà de la performance des modèles : la prédiction de liens peut-elle enrichir des graphes lexico-sémantiques du français ?

Résumé

This paper presents a resource-centric study of link prediction approaches over French lexical-semantic graphs. Our study incorporates two graphs, RezoJDM16k and RL-fr, and we evaluated seven link prediction models, with CompGCN-ConvE emerging as the best performer. We also conducted a qualitative analysis of the predictions using manual annotations. Based on this, we found that predictions with higher confidence scores were more valid for inclusion. Our findings highlight different benefits for the dense graph RezoJDM16k compared to the sparser graph RL-fr. While the addition of new triples to RezoJDM16k offers limited advantages, RL-fr can benefit substantially from our approach.
Fichier principal
Vignette du fichier
LREC_COLING2024-VF.pdf (1.2 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04537462 , version 1 (08-04-2024)

Identifiants

  • HAL Id : hal-04537462 , version 1

Citer

Hee-Soo Choi, Priyansh Trivedi, Mathieu Constant, Karën Fort, Bruno Guillaume. Beyond Model Performance: Can Link Prediction Enrich French Lexical Graphs?. The 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING), May 2024, Turin, Italy. ⟨hal-04537462⟩
4 Consultations
1 Téléchargements

Partager

Gmail Facebook X LinkedIn More