Investigating Capsule Networks with Dynamic Routing for Text Classification

TL;DR

This paper investigates the application of capsule networks with dynamic routing to text classification, proposing stabilization strategies and demonstrating state-of-the-art results on multiple benchmarks.

Contribution

It introduces the first empirical study of capsule networks for text modeling, with novel stabilization strategies for dynamic routing in this context.

Findings

Capsule networks achieve state-of-the-art on 4 out of 6 datasets.

Significant improvement in multi-label text classification.

Effective stabilization strategies for dynamic routing.

Abstract

In this study, we explore capsule networks with dynamic routing for text classification. We propose three strategies to stabilize the dynamic routing process to alleviate the disturbance of some noise capsules which may contain "background" information or have not been successfully trained. A series of experiments are conducted with capsule networks on six text classification benchmarks. Capsule networks achieve state of the art on 4 out of 6 datasets, which shows the effectiveness of capsule networks for text classification. We additionally show that capsule networks exhibit significant improvement when transfer single-label to multi-label text classification over strong baseline methods. To the best of our knowledge, this is the first work that capsule networks have been empirically investigated for text modeling.