Titre :

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

Auteur(s) :

Cripwell, Liam [Auteur]
Natural Language Processing : representations, inference and semantics [SYNALP]
Legrand, Joël [Auteur]
Natural Language Processing : representations, inference and semantics [SYNALP]
Machine Learning in Information Networks [MAGNET]
Gardent, Claire [Auteur]
Natural Language Processing : representations, inference and semantics [SYNALP]

Titre de la manifestation scientifique :

2023 Conference on Empirical Methods in Natural Language Processing

Ville :

Singapore

Pays :

Singapour

Date de début de la manifestation scientifique :

2023-12-06

Titre de l’ouvrage :

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Éditeur :

Association for Computational Linguistics

Discipline(s) HAL :

Informatique [cs]

Résumé en anglais : [en]

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 ...
Lire la suite >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.Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Collections :

• Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL