Integrating bi-dynamic routing capsule network with label-constraint for text classification

Xiang Guo, Youquan Wang*, Kaiyuan Gao, Jie Cao, Haicheng Tao, Chaoyue Chen

*Corresponding author for this work

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review

Abstract

Neural-based text classification methods have attracted increasing attention in recent years. Unlike the standard text classification methods, neural-based text classification methods perform the representation operation and end-to-end learning on the text data. Many useful insights can be derived from neural based text classifiers as demonstrated by an ever-growing body of work focused on text mining. However, in the real-world, text can be both complex and noisy which can pose a problem for effective text classification. An effective way to deal with this issue is to incorporate self-attention and capsule networks into text mining solutions. In this paper, we propose a Bi-dynamic routing Capsule Network with Label-constraint (BCNL) model for text classification, which moves beyond the limitations of previous methods by automatically learning the task-relevant and label-relevant words of text. Specifically, we use a Bi-LSTM and self-attention with position encoder network to learn text embeddings. Meanwhile, we propose a bi-dynamic routing capsule network with label-constraint to adjust the category distribute of text capsules. Through extensive experiments on four datasets, we observe that our method outperforms state-of-the-art baseline methods.

Original languageEnglish
Title of host publicationProceedings - 11th IEEE International Conference on Knowledge Graph, ICKG 2020
EditorsEnhong Chen, Grigoris Antoniou, Xindong Wu, Vipin Kumar
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages4-11
Number of pages8
ISBN (Electronic)9781728181561
DOIs
Publication statusPublished - Aug 2020
Externally publishedYes
Event11th IEEE International Conference on Knowledge Graph, ICKG 2020 - Virtual, Nanjing, China
Duration: 9 Aug 202011 Aug 2020

Publication series

NameProceedings - 11th IEEE International Conference on Knowledge Graph, ICKG 2020

Conference

Conference11th IEEE International Conference on Knowledge Graph, ICKG 2020
Country/TerritoryChina
CityVirtual, Nanjing
Period9/08/2011/08/20

Keywords

  • BiDynamic Routing
  • Capsule Network
  • Self-Attention
  • Text Classification

Fingerprint

Dive into the research topics of 'Integrating bi-dynamic routing capsule network with label-constraint for text classification'. Together they form a unique fingerprint.

Cite this