Text Classification using Capsules

TL;DR

This paper investigates the application of capsule networks to text classification, demonstrating their potential and advantages over CNNs, while proposing a more efficient routing method validated on benchmark datasets.

Contribution

It introduces a simple routing method for capsule networks that reduces computational complexity and demonstrates their effectiveness in text classification tasks.

Findings

Capsule networks perform comparably to CNNs on benchmark datasets.

The proposed routing method reduces computational complexity.

Capsule networks show advantages over CNNs in text classification.

Abstract

This paper presents an empirical exploration of the use of capsule networks for text classification. While it has been shown that capsule networks are effective for image classification, their validity in the domain of text has not been explored. In this paper, we show that capsule networks indeed have the potential for text classification and that they have several advantages over convolutional neural networks. We further suggest a simple routing method that effectively reduces the computational complexity of dynamic routing. We utilized seven benchmark datasets to demonstrate that capsule networks, along with the proposed routing method provide comparable results.