Enhancing AMR-to-Text Generation with Dual Graph Representations - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Enhancing AMR-to-Text Generation with Dual Graph Representations

Résumé

Generating text from graph-based data, such as Abstract Meaning Representation (AMR), is a challenging task due to the inherent difficulty in how to properly encode the structure of a graph with labeled edges. To address this difficulty , we propose a novel graph-to-sequence model that encodes different but complementary perspectives of the structural information contained in the AMR graph. The model learns parallel top-down and bottom-up representations of nodes capturing contrasting views of the graph. We also investigate the use of different node message passing strategies, employing different state-of-the-art graph en-coders to compute node representations based on incoming and outgoing perspectives. In our experiments, we demonstrate that the dual graph representation leads to improvements in AMR-to-text generation, achieving state-of-the-art results on two AMR datasets.
Fichier principal
Vignette du fichier
emnlp2019_ribeiro.pdf (960.56 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02277053 , version 1 (03-09-2019)

Identifiants

Citer

Leonardo F R Ribeiro, Claire Gardent, Iryna Gurevych. Enhancing AMR-to-Text Generation with Dual Graph Representations. 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Nov 2019, Hong Kong, China. pp.3181--3192, ⟨10.18653/v1/D19-1314⟩. ⟨hal-02277053⟩
63 Consultations
256 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More