Do Convolutional Networks need to be Deep for Text Classification ? - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

Do Convolutional Networks need to be Deep for Text Classification ?

Résumé

We study in this work the importance of depth in convolutional models for text classification, either when character or word inputs are considered. We show on 5 standard text classification and sentiment analysis tasks that deep models indeed give better performances than shallow networks when the text input is represented as a sequence of characters. However, a simple shallow-and-wide network outper-forms deep models such as DenseNet with word inputs. Our shallow word model further establishes new state-of-the-art performances on two datasets: Yelp Binary (95.9%) and Yelp Full (64.9%).
Fichier principal
Vignette du fichier
1707.04108.pdf (450.73 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01690601 , version 1 (24-02-2019)

Identifiants

  • HAL Id : hal-01690601 , version 1

Citer

Hoa T. Le, Christophe Cerisara, Alexandre Denis. Do Convolutional Networks need to be Deep for Text Classification ?. AAAI Workshop on Affective Content Analysis, Feb 2018, New Orleans, United States. ⟨hal-01690601⟩
350 Consultations
557 Téléchargements

Partager

Gmail Facebook X LinkedIn More