Communication Dans Un Congrès Année : 2016

Multi-view and multi-task training of RST discourse parsers

Résumé

We experiment with different ways of training LSTM networks to predict RST discourse trees. The main challenge for RST discourse parsing is the limited amounts of training data. We combat this by regularizing our models using task supervision from related tasks as well as alternative views on discourse structures. We show that a simple LSTM sequential discourse parser takes advantage of this multi-view and multi-task framework with 12-15% error reductions over our baseline (depending on the metric) and results that rival more complex state-of-the-art parsers.

Fichier principal
Vignette du fichier
C16-1179.pdf (170.6 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence
Loading...

Dates et versions

hal-02373867 , version 1 (21-11-2019)

Licence

Identifiants

  • HAL Id : hal-02373867 , version 1

Citer

Chloé Braud, Barbara Plank, Anders Søgaard. Multi-view and multi-task training of RST discourse parsers. Conference on Computational Linguistics (CoLing), Dec 2016, Osaka, Japan. pp.1903 - 1913. ⟨hal-02373867⟩
173 Consultations
185 Téléchargements

Partager

  • More