Semi-supervised experiments at LORIA for the SPMRL 2014 Shared Task

Christophe Cerisara 1, *
* Auteur correspondant
1 SYNALP - Natural Language Processing : representations, inference and semantics
LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : This paper describes the LORIA first participation at the SPMRL Shared Task. The focus of this work is on exploring several options to take advantage of the unlabeled data to improve the performances of a baseline dependency parser, which has neither be tuned to the specificities of the shared task nor evaluation languages. The semi-supervised approaches investigated include LDA word classes and super-tags predicted by a linear classifier trained with self-training. None of these options resulted in increased parsing accuracy.
Type de document :
Communication dans un congrès
Proc. of the Shared Task on Statistical Parsing of Morphologically Rich Languages, Aug 2014, Dublin, Ireland
Liste complète des métadonnées

Littérature citée [32 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01109886
Contributeur : Christophe Cerisara <>
Soumis le : mardi 27 janvier 2015 - 10:44:04
Dernière modification le : vendredi 9 février 2018 - 13:20:04
Document(s) archivé(s) le : mardi 28 avril 2015 - 10:25:58

Fichier

Loria_28_Paper.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01109886, version 1

Collections

Citation

Christophe Cerisara. Semi-supervised experiments at LORIA for the SPMRL 2014 Shared Task. Proc. of the Shared Task on Statistical Parsing of Morphologically Rich Languages, Aug 2014, Dublin, Ireland. 〈hal-01109886〉

Partager

Métriques

Consultations de la notice

194

Téléchargements de fichiers

137