Context-Aware Document Simplification - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Context-Aware Document Simplification

Résumé

To date, most work on text simplification has focused on sentence-level inputs. Early attempts at document simplification merely applied these approaches iteratively over the sentences of a document. However, this fails to coherently preserve the discourse structure, leading to suboptimal output quality. Recently, strategies from controllable simplification have been leveraged to achieve state-ofthe-art results on document simplification by first generating a document-level plan (a sequence of sentence-level simplification operations) and using this plan to guide sentencelevel simplification downstream. However, this is still limited in that the simplification model has no direct access to the local intersentence document context, likely having a negative impact on surface realisation. We explore various systems that use document context within the simplification process itself, either by iterating over larger text units or by extending the system architecture to attend over a high-level representation of document context. In doing so, we achieve state-of-the-art performance on the document simplification task, even when not relying on plan-guidance. Further, we investigate the performance and efficiency tradeoffs of system variants and make suggestions of when each should be preferred.
Fichier principal
Vignette du fichier
2023.findings-acl.834.pdf (3.32 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04369783 , version 1 (02-01-2024)

Licence

Paternité

Identifiants

Citer

Liam Cripwell, Joël Legrand, Claire Gardent. Context-Aware Document Simplification. Findings of the Association for Computational Linguistics: ACL 2023, ACL, Jul 2023, Toronto, Canada. pp.13190-13206, ⟨10.18653/v1/2023.findings-acl.834⟩. ⟨hal-04369783⟩
38 Consultations
7 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More