Generating Elliptic Coordination

Claire Gardent 1 Shashi Narayan 1
1 SYNALP - Natural Language Processing : representations, inference and semantics
LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : In this paper, we focus on the task of generating elliptic sentences. We extract from the data provided by the Surface Realisation (SR) Task 2398 input whose corresponding output sentence contain an ellipsis. We show that 9\% of the data contains an ellipsis and that both coverage and BLEU score markedly decrease for elliptic input (from 82.3% coverage for non-elliptic sentences to 65.3% for elliptic sentences and from 0.60 BLEU score to 0.47). We argue that elided material should be represented using phonetically empty nodes and we introduce a set of rewrite rules which permits adding these empty categories to the SR data. Finally, we evaluate an existing surface realiser on the resulting dataset. We show that, after rewriting, the generator achieves a coverage of 76% and a BLEU score of 0.74 on the elliptical data.
Type de document :
Communication dans un congrès
the 14th European Workshop on Natural Language Generation (ENLG), Aug 2013, Sofia, Bulgaria. pp.40-50, 2013
Liste complète des métadonnées

Littérature citée [44 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-00920606
Contributeur : Claire Gardent <>
Soumis le : mercredi 18 décembre 2013 - 19:10:02
Dernière modification le : mardi 24 avril 2018 - 13:35:24
Document(s) archivé(s) le : jeudi 20 mars 2014 - 11:26:38

Fichier

enlg2013-ellipsis.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00920606, version 1

Collections

Citation

Claire Gardent, Shashi Narayan. Generating Elliptic Coordination. the 14th European Workshop on Natural Language Generation (ENLG), Aug 2013, Sofia, Bulgaria. pp.40-50, 2013. 〈hal-00920606〉

Partager

Métriques

Consultations de la notice

172

Téléchargements de fichiers

265