Reusability of Mental Representation Theory in Automatic Generation: Generating Expressions Referring to Objects with G-TAG and RMs

Hélène Manuélian 1
1 LANGUE ET DIALOGUE - Human-machine dialogue with a significant language component
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : This paper deals with the way to automatically generate referring expressions by integrating the model of Mental Representation (RMs) in the lexicalized formalism of generation G-TAG. To achieve this purpose, the lexical part of RMs is extended by a history of the forms used in the text. Algorithms have been added in order to decide on how to lexicalize a concept.
Type de document :
Communication dans un congrès
Workshop on Analysis for Generation - International Natural Language Generation Conference 2000, 2000, Mitzpe Ramon, Israel, 2000
Liste complète des métadonnées

https://hal.inria.fr/inria-00099373
Contributeur : Publications Loria <>
Soumis le : mardi 26 septembre 2006 - 08:53:21
Dernière modification le : jeudi 11 janvier 2018 - 06:19:48

Identifiants

  • HAL Id : inria-00099373, version 1

Collections

Citation

Hélène Manuélian. Reusability of Mental Representation Theory in Automatic Generation: Generating Expressions Referring to Objects with G-TAG and RMs. Workshop on Analysis for Generation - International Natural Language Generation Conference 2000, 2000, Mitzpe Ramon, Israel, 2000. 〈inria-00099373〉

Partager

Métriques

Consultations de la notice

33