文章基本信息

标题：One-class Text Classification with Multi-modal Deep Support Vector Data Description
本地全文：下载
作者：Chenlong Hu ; Yukun Feng ; Hidetaka Kamigaito 等
期刊名称：Conference on European Chapter of the Association for Computational Linguistics (EACL)
出版年度：2021
卷号：2021
页码：3378-3390
DOI：10.18653/v1/2021.eacl-main.296
语种：English
出版社：ACL Anthology
摘要：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.