Parse correction with specialized models for difficult attachment types

Abstract : This paper develops a framework for syntactic dependency parse correction. Dependencies in an input parse tree are revised by selecting, for a given dependent, the best governor from within a small set of candidates. We use a discriminative linear ranking model to select the best governor from a group of candidates for a dependent, and our model includes a rich feature set that encodes syntactic structure in the input parse tree. The parse correction framework is parser-agnostic, and can correct attachments using either a generic model or specialized models tailored to difficult attachment types like coordination and pp-attachment. Our experiments show that parse correction, combining a generic model with specialized models for difficult attachment types, can successfully improve the quality of predicted parse trees output by several representative state-of-the-art dependency parsers for French.
Type de document :
Communication dans un congrès
EMNLP 2011 - The 2011 Conference on Empirical Methods in Natural Language Processing, Jul 2011, Edinburgh, United Kingdom. To appear, 2011
Liste complète des métadonnées

Littérature citée [32 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-00602083
Contributeur : Enrique Henestroza Anguiano <>
Soumis le : mardi 21 juin 2011 - 14:45:55
Dernière modification le : vendredi 4 janvier 2019 - 17:33:24
Document(s) archivé(s) le : jeudi 22 septembre 2011 - 02:25:26

Fichier

henestroza2011parse.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00602083, version 1

Collections

Citation

Enrique Henestroza Anguiano, Marie Candito. Parse correction with specialized models for difficult attachment types. EMNLP 2011 - The 2011 Conference on Empirical Methods in Natural Language Processing, Jul 2011, Edinburgh, United Kingdom. To appear, 2011. 〈hal-00602083〉

Partager

Métriques

Consultations de la notice

255

Téléchargements de fichiers

115