2018/03/29 by Wei Zhao, Zhao, Wei, Jianbo Ye +9 · 1 voice · 101 citations
Computer Science · #Adaptive routing #Artificial Intelligence (cs.AI) #Artificial intelligence #Baseline (sea) #Capsule #Computation and Language (cs.CL) #Computer network #Computer science #Data mining #FOS: Computer and information sciences #Machine learning #Noise (video) #Pattern recognition (psychology) #Process (computing) #Routing (electronic design automation) #Routing protocol #Sentiment Analysis and Opinion Mining #Spam and Phishing Detection #Static routing #Text and Document Classification Technologies #cs.AI #cs.CL
paper · pdf · doi:10.48550/arxiv.1804.00538
published in arXiv (Cornell University) (Cornell University) · 12 pages
openalex publication_date 2018/03/29 · arxiv published 2018/03/29 · arxiv created 2018/09/03 · arxiv updated 2018/09/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
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.