Investigating Capsule Networks with Dynamic Routing for Text Classification
This work addresses text classification for NLP applications, presenting an incremental improvement with novel stabilization strategies for capsule networks.
The study tackled text classification by exploring capsule networks with dynamic routing, achieving state-of-the-art results on 4 out of 6 benchmark datasets and showing significant improvement in multi-label classification over strong baselines.
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.