Investigating Capsule Networks with Dynamic Routing for Text Classification
Authors:
- Min YangMin Yang
- Suofei ZhangSZSuofei Zhang
Preprint
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.Keywords
All Related Versions
This publication has 4 references indexed in Scilit:
- Contextual Bidirectional Long Short-Term Memory Recurrent Neural Network Language Models: A Generative Approach to Sentiment Analysis2017
- Linguistically Regularized LSTM for Sentiment Classification2017
- Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation2014
- Large-Scale Bayesian Logistic Regression for Text CategorizationTechnometrics, 2007