Syntax and Data-to-Text Generation

Claire Gardent 1, *
* Auteur correspondant
1 SYNALP - Natural Language Processing : representations, inference and semantics
LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : 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.
Type de document :
Chapitre d'ouvrage
Lecture Notes in Computer Science, 8791, pp.3 - 20, 2014, 〈10.1007/978-3-319-11397-5_1〉
Liste complète des métadonnées

Littérature citée [39 références]  Voir  Masquer  Télécharger
Contributeur : Claire Gardent <>
Soumis le : lundi 26 janvier 2015 - 16:52:32
Dernière modification le : mardi 18 décembre 2018 - 16:38:01
Document(s) archivé(s) le : lundi 27 avril 2015 - 10:47:50


Fichiers produits par l'(les) auteur(s)




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〉



Consultations de la notice


Téléchargements de fichiers