One-class Text Classification with Multi-modal Deep Support Vector Data Description

Chenlong Hu, Yukun Feng, Hidetaka Kamigaito, Hiroya Takamura, Manabu Okumura


Abstract
This work presents multi-modal deep SVDD (mSVDD) for one-class text classification. By extending the uni-modal SVDD to a multiple modal one, we build mSVDD with multiple hyperspheres, that enable us to build a much better description for target one-class data. Additionally, the end-to-end architecture of mSVDD can jointly handle neural feature learning and one-class text learning. We also introduce a mechanism for incorporating negative supervision in the absence of real negative data, which can be beneficial to the mSVDD model. We conduct experiments on Reuters and 20 Newsgroup datasets, and the experimental results demonstrate that mSVDD outperforms uni-modal SVDD and mSVDD can get further improvements when negative supervision is incorporated.
Anthology ID:
2021.eacl-main.296
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Month:
April
Year:
2021
Address:
Online
Editors:
Paola Merlo, Jorg Tiedemann, Reut Tsarfaty
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3378–3390
Language:
URL:
https://aclanthology.org/2021.eacl-main.296
DOI:
10.18653/v1/2021.eacl-main.296
Bibkey:
Cite (ACL):
Chenlong Hu, Yukun Feng, Hidetaka Kamigaito, Hiroya Takamura, and Manabu Okumura. 2021. One-class Text Classification with Multi-modal Deep Support Vector Data Description. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 3378–3390, Online. Association for Computational Linguistics.
Cite (Informal):
One-class Text Classification with Multi-modal Deep Support Vector Data Description (Hu et al., EACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.eacl-main.296.pdf
Data
WikiText-2