Using Paraphrases and Lexical Semantics to Improve the Accuracy and the Robustness of Supervised Models in Situated Dialogue Systems

Claire Gardent 1 Lina Maria Rojas Barahona 1
1 SYNALP - Natural Language Processing : representations, inference and semantics
LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : This paper explores to what extent lemmatisation, lexical resources, distributional semantics and paraphrases can increase the accuracy of supervised models for dialogue management. The results suggest that each of these factors can help improve performance but that the impact will vary depending on their combination and on the evaluation mode.
Type de document :
Communication dans un congrès
Conference on Empirical Methods in Natural Language Processing, Oct 2013, Seattle, United States. pp.808-813, 2013
Liste complète des métadonnées

Littérature citée [11 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00905405
Contributeur : Lina Maria Rojas Barahona <>
Soumis le : lundi 18 novembre 2013 - 11:21:23
Dernière modification le : jeudi 11 janvier 2018 - 06:23:43
Document(s) archivé(s) le : samedi 8 avril 2017 - 00:18:39

Fichier

D13-1076.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00905405, version 1

Collections

Citation

Claire Gardent, Lina Maria Rojas Barahona. Using Paraphrases and Lexical Semantics to Improve the Accuracy and the Robustness of Supervised Models in Situated Dialogue Systems. Conference on Empirical Methods in Natural Language Processing, Oct 2013, Seattle, United States. pp.808-813, 2013. 〈hal-00905405〉

Partager

Métriques

Consultations de la notice

399

Téléchargements de fichiers

369