Benchmarking of Statistical Dependency Parsers for French

Abstract : We compare the performance of three statistical parsing architectures on the problem of deriving typed dependency structures for French. The architectures are based on PCFGs with latent variables, graph-based dependency parsing and transition-based dependency parsing, respectively. We also study the influence of three types of lexical information: lemmas, morphological features, and word clusters. The results show that all three systems achieve competitive performance, with a best labeled attachment score over 88%. All three parsers benefit from the use of automatically derived lemmas, while morphological features seem to be less important. Word clusters have a positive effect primarily on the latent variable parser.
Type de document :
Communication dans un congrès
23rd International Conference on Computational Linguistics - COLING 2010, Aug 2010, Beijing, China. Coling 2010 Organizing Committee, pp.108-116, 2010
Liste complète des métadonnées

Littérature citée [39 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-00514815
Contributeur : Marie Candito <>
Soumis le : mardi 7 septembre 2010 - 15:36:54
Dernière modification le : vendredi 4 janvier 2019 - 17:33:24
Document(s) archivé(s) le : mercredi 8 décembre 2010 - 02:29:53

Fichier

frdepcompar-Coling10-final.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00514815, version 1

Collections

Citation

Marie Candito, Joakim Nivre, Pascal Denis, Enrique Henestroza Anguiano. Benchmarking of Statistical Dependency Parsers for French. 23rd International Conference on Computational Linguistics - COLING 2010, Aug 2010, Beijing, China. Coling 2010 Organizing Committee, pp.108-116, 2010. 〈hal-00514815〉

Partager

Métriques

Consultations de la notice

363

Téléchargements de fichiers

200