Hierarchical Multi-label Classification of Text with Capsule Networks
TL
TL;DR
This paper applies and compares simple shallow capsule networks for hierarchical multi-label text classification and shows that they can perform superior to other neural networks, and non-neural network architectures such as SVMs.
Abstract
Capsule networks have been shown to demonstrate good performance on structured data in the area of visual inference. In this paper we apply and compare simple shallow capsule networks for hierarchical multi-label text classification and show that they can perform superior to other neural networks, such as CNNs and LSTMs, and non-neural network architectures such as SVMs. For our experiments, we use the established Web of Science (WOS) dataset and introduce a new real-world scenario dataset, the BlurbGenreCollection (BGC). Our results confirm the hypothesis that capsule networks are especially advantageous for rare events and structurally diverse categories, which we attribute to their ability to combine latent encoded information.
References25 items
1
Attention-Based Capsule Networks with Dynamic Routing for Relation Extraction
2
Sentylic at IEST 2018: Gated Recurrent Neural Network and Capsule Network Based Approach for Implicit Emotion Detection
3
Zero-shot User Intent Detection via Capsule Neural Networks
4
A Capsule Network-based Embedding Model for Knowledge Graph Completion and Search Personalization
5