Improving Recurrent Neural Networks For Sequence Labelling - Archive ouverte HAL Accéder directement au contenu
Autre Publication Scientifique Année : 2016

Improving Recurrent Neural Networks For Sequence Labelling

Résumé

In this paper we study different types of Recurrent Neural Networks (RNN) for sequence labeling tasks. We propose two new variants of RNNs integrating improvements for sequence labeling, and we compare them to the more traditional Elman and Jordan RNNs. We compare all models, either traditional or new, on four distinct tasks of sequence labeling: two on Spoken Language Understanding (ATIS and MEDIA); and two of POS tagging for the French Treebank (FTB) and the Penn Treebank (PTB) corpora. The results show that our new variants of RNNs are always more effective than the others.
Fichier principal
Vignette du fichier
2016_arXiv_NewRNN_author-final.pdf (409.92 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01489976 , version 1 (14-03-2017)

Identifiants

  • HAL Id : hal-01489976 , version 1

Citer

Marco Dinarelli, Isabelle Tellier. Improving Recurrent Neural Networks For Sequence Labelling. 2016. ⟨hal-01489976⟩
243 Consultations
979 Téléchargements

Partager

Gmail Facebook X LinkedIn More