A Symbolic Approach to Near-Deterministic Surface Realisation using Tree Adjoining Grammar

Claire Gardent 1 Eric Kow 1
1 TALARIS - Natural Language Processing: representation, inference and semantics
Inria Nancy - Grand Est, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : Surface realisers divide into those used in generation (NLG geared realisers) and those mirroring the parsing process (Reversible realisers). While the first rely on grammars not easily usable for parsing, it is unclear how the second type of realisers could be parameterised to yield from among the set of possible paraphrases, the paraphrase appropriate to a given generation context. In this paper, we present a surface realiser which combines a reversible grammar (used for parsing and doing semantic construction) with a symbolic means of selecting paraphrases.
Keywords : generation TAG paraphrase
Type de document :
Communication dans un congrès
45th Annual Meeting of the Association for Computational Linguistics - ACL 2007, Jun 2007, Prague, Czech Republic. Association for Computational Linguistics, pp.328-335, 2007
Liste complète des métadonnées

Littérature citée [17 références]  Voir  Masquer  Télécharger
https://hal.inria.fr/inria-00149366
Contributeur : Eric Kow <>
Soumis le : vendredi 25 mai 2007 - 14:20:26
Dernière modification le : jeudi 11 janvier 2018 - 06:21:35
Document(s) archivé(s) le : jeudi 8 avril 2010 - 17:53:40

Fichier

acl07-garkow.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00149366, version 1

Collections

INRIA | LORIA | UNIV-LORRAINE

Citation

Claire Gardent, Eric Kow. A Symbolic Approach to Near-Deterministic Surface Realisation using Tree Adjoining Grammar. 45th Annual Meeting of the Association for Computational Linguistics - ACL 2007, Jun 2007, Prague, Czech Republic. Association for Computational Linguistics, pp.328-335, 2007. 〈inria-00149366〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

209

Téléchargements de fichiers

190

Contact


archive-ouverte@inria.fr