Simplicity Level Estimate (SLE): A Learned Reference-Less Metric for Sentence Simplification - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Simplicity Level Estimate (SLE): A Learned Reference-Less Metric for Sentence Simplification

Résumé

Automatic evaluation for sentence simplification remains a challenging problem. Most popular evaluation metrics require multiple high-quality references-something not readily available for simplification-which makes it difficult to test performance on unseen domains. Furthermore, most existing metrics conflate simplicity with correlated attributes such as fluency or meaning preservation. We propose a new learned evaluation metric (SLE) which focuses on simplicity, outperforming almost all existing metrics in terms of correlation with human judgements.
Fichier principal
Vignette du fichier
2023.emnlp-main.739.pdf (226.55 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Licence : CC BY - Paternité

Dates et versions

hal-04369824 , version 1 (02-01-2024)

Identifiants

Citer

Liam Cripwell, Joël Legrand, Claire Gardent. Simplicity Level Estimate (SLE): A Learned Reference-Less Metric for Sentence Simplification. 2023 Conference on Empirical Methods in Natural Language Processing, Dec 2023, Singapore, Singapore. pp.12053-12059, ⟨10.18653/v1/2023.emnlp-main.739⟩. ⟨hal-04369824⟩
26 Consultations
7 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More