A MDL-based Model of Gender Knowledge Acquisition

Abstract : This paper presents an iterative model of knowledge acquisition of gender information associated with word endings in French. Gender knowledge is represented as a set of rules containing exceptions. Our model takes noun-gender pairs as input and constantly maintains a list of rules and exceptions which is both coherent with the input data and minimal with respect to a minimum description length criterion. This model was compared to human data at various ages and showed a good fit. We also compared the kind of rules discovered by the model with rules usually extracted by linguists and found interesting discrepancies.
Type de document :
Communication dans un congrès
Alex Clark and Kristina Toutanova. 12th Conference on Natural Language Learning (CoNLL-2008), Aug 2008, Manchester, United Kingdom. Association for Computational Linguistics, pp.73-80, 2008
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00311720
Contributeur : Benoît Lemaire <>
Soumis le : mercredi 20 août 2008 - 14:45:30
Dernière modification le : jeudi 11 octobre 2018 - 08:48:04
Document(s) archivé(s) le : vendredi 5 octobre 2012 - 11:48:37

Fichier

coNLL08.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

  • HAL Id : hal-00311720, version 1

Collections

Citation

Harmony Marchal, Benoît Lemaire, Maryse Bianco, Philippe Dessus. A MDL-based Model of Gender Knowledge Acquisition. Alex Clark and Kristina Toutanova. 12th Conference on Natural Language Learning (CoNLL-2008), Aug 2008, Manchester, United Kingdom. Association for Computational Linguistics, pp.73-80, 2008. 〈hal-00311720〉

Partager

Métriques

Consultations de la notice

237

Téléchargements de fichiers

159