Hierarchical Multi-label Classification of Text with Capsule Networks

Rami Aly, Steffen Remus, Chris Biemann


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.
Anthology ID:
P19-2045
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop
Month:
July
Year:
2019
Address:
Florence, Italy
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
323–330
Language:
URL:
https://aclanthology.org/P19-2045
DOI:
10.18653/v1/P19-2045
Bibkey:
Cite (ACL):
Rami Aly, Steffen Remus, and Chris Biemann. 2019. Hierarchical Multi-label Classification of Text with Capsule Networks. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, pages 323–330, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Hierarchical Multi-label Classification of Text with Capsule Networks (Aly et al., ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-2045.pdf
Code
 uhh-lt/BlurbGenreCollection-HMC
Data
WOS