Quantifying training challenges of dependency parsers - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

Quantifying training challenges of dependency parsers

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

Résumé

Not all dependencies are equal when training a dependency parser: some are straightforward enough to be learned with only a sample of data, others embed more complexity. This work introduces a series of metrics to quantify those differences, and thereby to expose the shortcomings of various parsing algorithms and strategies. Apart from a more thorough comparison of parsing systems, these new tools also prove useful for characterizing the information conveyed by cross-lingual parsers, in a quantitative but still interpretable way.

Mots clés

Fichier principal
Vignette du fichier
C18-1270.pdf (250.56 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...

Dates et versions

hal-01907772 , version 1 (29-10-2018)

Identifiants

  • HAL Id : hal-01907772 , version 1

Citer

Lauriane Aufrant, Guillaume Wisniewski, François Yvon. Quantifying training challenges of dependency parsers. International Conference on Computational Linguistics, Aug 2018, Santa Fe, New Mexico, United States. pp.3191 - 3202. ⟨hal-01907772⟩
41 Consultations
22 Téléchargements

Partager

Gmail Facebook X LinkedIn More