Exploiting Dynamic Oracles to Train Projective Dependency Parsers on Non-Projective Trees - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

Exploiting Dynamic Oracles to Train Projective Dependency Parsers on Non-Projective Trees

Lauriane Aufrant
  • Fonction : Auteur
  • PersonId : 980416
Guillaume Wisniewski
François Yvon

Résumé

Because the most common transition systems are projective, training a transition-based dependency parser often implies to either ignore or rewrite the non-projective training examples, which has an adverse impact on accuracy. In this work, we propose a simple modification of dynamic oracles, which enables the use of non-projective data when training projective parsers. Evaluation on 73~treebanks shows that our method achieves significant gains (+2 to +7 UAS for the most non-projective languages) and consistently outperforms traditional projectivization and pseudo-projectivization approaches.
Fichier principal
Vignette du fichier
N18-2066.pdf (172.19 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-01813394 , version 1 (18-07-2018)

Identifiants

  • HAL Id : hal-01813394 , version 1

Citer

Lauriane Aufrant, Guillaume Wisniewski, François Yvon. Exploiting Dynamic Oracles to Train Projective Dependency Parsers on Non-Projective Trees. Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, ACL, Jun 2018, New Orleans, United States. pp.413 - 419. ⟨hal-01813394⟩
102 Consultations
105 Téléchargements

Partager

Gmail Facebook X LinkedIn More