Label-dependency coding in Simple Recurrent Networks for Spoken Language Understanding

Abstract : Modelling target label dependencies is important for sequence labelling tasks. This may become crucial in the case of Spoken Language Understanding (SLU) applications, especially for the slot-filling task where models have to deal often with a high number of target labels. Conditional Random Fields (CRF) were previously considered as the most efficient algorithm in these conditions. More recently, different architectures of Recurrent Neural Networks (RNNs) have been proposed for the SLU slot-filling task. Most of them, however, have been successfully evaluated on the simple ATIS database, on which it is difficult to draw significant conclusions. In this paper we propose new variants of RNNs able to learn efficiently and effectively label dependencies by integrating label embeddings. We show first that modeling label dependencies is useless on the (simple) ATIS database and unstructured models can produce state-of-the-art results on this benchmark. On ATIS our new variants achieve the same results as state-of-the-art models, while being much simpler. On the other hand, on the MEDIA benchmark, we show that the modification introduced in the proposed RNN outperforms traditional RNNs and CRF models.
Type de document :
Communication dans un congrès
Interspeech, Aug 2017, Stockholm, Sweden. 〈〉
Liste complète des métadonnées

Littérature citée [24 références]  Voir  Masquer  Télécharger
Contributeur : Christian Raymond <>
Soumis le : lundi 3 juillet 2017 - 16:58:22
Dernière modification le : lundi 17 décembre 2018 - 09:06:01
Document(s) archivé(s) le : jeudi 14 décembre 2017 - 22:58:16


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-01553830, version 1


Marco Dinarelli, Vedran Vukotić, Christian Raymond. Label-dependency coding in Simple Recurrent Networks for Spoken Language Understanding. Interspeech, Aug 2017, Stockholm, Sweden. 〈〉. 〈hal-01553830〉



Consultations de la notice


Téléchargements de fichiers