Convolutions Are All You Need (For Classifying Character Sequences)

Zach Wood-Doughty, Nicholas Andrews, Mark Dredze

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

While recurrent neural networks (RNNs) are widely used for text classification, they demonstrate poor performance and slow convergence when trained on long sequences. When text is modeled as characters instead of words, the longer sequences make RNNs a poor choice. Convolutional neural networks (CNNs), although somewhat less ubiquitous than RNNs, have an internal structure more appropriate for long-distance character dependencies. To better understand how CNNs and RNNs differ in handling long sequences, we use them for text classification tasks in several character-level social media datasets. The CNN models vastly outperform the RNN models in our experiments, suggesting that CNNs are superior to RNNs at learning to classify character-level data.

Original languageEnglish (US)
Title of host publication4th Workshop on Noisy User-Generated Text, W-NUT 2018 - Proceedings of the Workshop
PublisherAssociation for Computational Linguistics (ACL)
Pages208-213
Number of pages6
ISBN (Electronic)9781948087797
StatePublished - 2018
Externally publishedYes
Event4th Workshop on Noisy User-Generated Text, W-NUT 2018 - Brussels, Belgium
Duration: Nov 1 2018 → …

Publication series

Name4th Workshop on Noisy User-Generated Text, W-NUT 2018 - Proceedings of the Workshop

Conference

Conference4th Workshop on Noisy User-Generated Text, W-NUT 2018
Country/TerritoryBelgium
CityBrussels
Period11/1/18 → …

ASJC Scopus subject areas

  • Information Systems
  • Computer Science Applications
  • Computational Theory and Mathematics

Fingerprint

Dive into the research topics of 'Convolutions Are All You Need (For Classifying Character Sequences)'. Together they form a unique fingerprint.

Cite this