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
- 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
- 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)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/2021.eacl-main.296.pdf
- Data
- WikiText-2