Investigating Capsule Networks with Dynamic Routing for Text Classification
文献类型：会议论文
| 作者 | Wei Zhao; Jianbo Ye; Min Yang; Zeyang Lei; Soufei Zhang; Zhou Zhao |
| 出版日期 | 2018 |
| 会议日期 | 2018 |
| 会议地点 | 比利时 |
| 英文摘要 | In this study, we explore capsule networks with dynamic routing for text classifica- tion. We propose three strategies to sta- bilize the dynamic routing process to al- leviate the disturbance of some noise cap- sules which may contain “background” in- formation or have not been successfully trained. A series of experiments are con- ducted with capsule networks on six text classification benchmarks. Capsule net- works achieve competitive results over the compared baseline methods on 4 out of 6 datasets, which shows the effectiveness of capsule networks for text classifica- tion. We additionally show that capsule networks exhibit significant improvement when transfer single-label to multi-label text classification over the competitors. To the best of our knowledge, this is the first work that capsule networks have been em- pirically investigated for text modeling1 |
| 语种 | 英语 |
| 源URL | [http://ir.siat.ac.cn:8080/handle/172644/14101]  |
| 专题 | 深圳先进技术研究院_数字所 |
| 推荐引用方式 GB/T 7714 | Wei Zhao,Jianbo Ye,Min Yang,et al. Investigating Capsule Networks with Dynamic Routing for Text Classification[C]. 见:. 比利时. 2018. |
入库方式： OAI收割
来源：深圳先进技术研究院
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。