Syntax and Data-to-Text Generation - Archive ouverte HAL Accéder directement au contenu
Chapitre D'ouvrage Année : 2014

Syntax and Data-to-Text Generation

Résumé

With the development of the web of data, recent statisti-cal, data-to-text generation approaches have focused on mapping data (e.g., database records or knowledge-base (KB) triples) to natural lan-guage. In contrast to previous grammar-based approaches, this more recent work systematically eschews syntax and learns a direct mapping between meaning representations and natural language. By contrast, I argue that an explicit model of syntax can help support NLG in sev-eral ways. Based on case studies drawn from KB-to-text generation, I show that syntax can be used to support supervised training with little training data; to ensure domain portability; and to improve statistical hypertagging.
Fichier principal
Vignette du fichier
gardentSLSP14.pdf (171.52 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01109617 , version 1 (26-01-2015)

Identifiants

Citer

Claire Gardent. Syntax and Data-to-Text Generation. Lecture Notes in Computer Science, 8791, pp.3 - 20, 2014, ⟨10.1007/978-3-319-11397-5_1⟩. ⟨hal-01109617⟩
156 Consultations
1120 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More