Do Convolutional Networks need to be Deep for Text Classification ? - Archive ouverte HAL Access content directly
Conference Papers Year : 2018

Do Convolutional Networks need to be Deep for Text Classification ?

Abstract

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
Origin Files produced by the author(s)
Loading...

Dates and versions

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

Identifiers

  • HAL Id : hal-01690601 , version 1

Cite

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⟩
351 View
560 Download

Share

Gmail Mastodon Facebook X LinkedIn More