Using FB-LTAG Derivation Trees to Generate Transformation-Based Grammar Exercices

Claire Gardent 1 Laura Perez-Beltrachini 1
1 SYNALP - Natural Language Processing : representations, inference and semantics
LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : Using a Feature-Based Lexicalised Tree Adjoining Grammar (FB-LTAG), we present an approach for generating pairs of sentences that are related by a syntactic transformation and we apply this approach to create language learning exercises. We argue that the derivation trees of an FB-LTAG provide a good level of representation for capturing syntactic transformations. We relate our approach to previous work on sentence reformulation, question generation and grammar exercise generation. We evaluate precision and linguistic coverage. And we demonstrate the genericity of the proposal by applying it to a range of transformations including the Passive/Active transformation, the pronominalisation of an NP, the assertion / yes-no question relation and the assertion / wh-question transformation.
Type de document :
Communication dans un congrès
TAG+11: The 11th International Workshop on Tree Adjoining Grammars and Related Formalisms, Sep 2012, Paris, France. pp.117-125, 2012
Liste complète des métadonnées

Littérature citée [14 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-00768231
Contributeur : Claire Gardent <>
Soumis le : vendredi 21 décembre 2012 - 09:31:53
Dernière modification le : mardi 24 avril 2018 - 13:33:20
Document(s) archivé(s) le : dimanche 18 décembre 2016 - 07:51:42

Fichier

tag_1114.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00768231, version 1

Collections

Citation

Claire Gardent, Laura Perez-Beltrachini. Using FB-LTAG Derivation Trees to Generate Transformation-Based Grammar Exercices. TAG+11: The 11th International Workshop on Tree Adjoining Grammars and Related Formalisms, Sep 2012, Paris, France. pp.117-125, 2012. 〈hal-00768231〉

Partager

Métriques

Consultations de la notice

317

Téléchargements de fichiers

207