Generating Text from Anonymised Structures - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Generating Text from Anonymised Structures

Résumé

Surface realisation maps a meaning representation (MR) to a text, usually a single sentence. In this paper, we introduce a new parallel dataset of deep meaning representations and French sentences and we present a novel method for MR-to-text generation which seeks to generalise by abstracting away from lexical content. Most current work on natural language generation focuses on generating text that matches a reference using BLEU as evaluation criteria. In this paper, we additionally consider the model's ability to reintroduce the function words that are absent from the deep input meaning representations. We show that our approach increases both BLEU score and the scores used to assess function words generation .
Fichier principal
Vignette du fichier
W19-8614-INLG-emilie.pdf (515.83 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-02460312 , version 1 (31-01-2020)

Identifiants

  • HAL Id : hal-02460312 , version 1

Citer

Emilie Colin, Claire Gardent. Generating Text from Anonymised Structures. Proceedings of the 12th International Conference on Natural Language Generation, Oct 2019, Hong Kong, China. pp.112 - 117. ⟨hal-02460312⟩
34 Consultations
37 Téléchargements

Partager

Gmail Facebook X LinkedIn More