论文标题
对抗性多二进制神经网络，用于多级分类
Adversarial Multi-Binary Neural Network for Multi-class Classification
论文作者
论文摘要
多级文本分类是机器学习和自然语言处理的关键问题之一。新兴的神经网络使用多输出软磁性层处理问题并取得了实质性的进步，但它们没有明确学习类之间的相关性。在本文中，我们使用多任务框架来解决多级分类，其中多级分类器和多个二进制分类器一起训练。此外，我们采用对抗性培训来区分特定班级的特征和类不足的特征。该模型受益于更好的功能表示。我们对两个大规模多级文本分类任务进行实验，并证明所提出的体系结构的表现优于基线方法。
Multi-class text classification is one of the key problems in machine learning and natural language processing. Emerging neural networks deal with the problem using a multi-output softmax layer and achieve substantial progress, but they do not explicitly learn the correlation among classes. In this paper, we use a multi-task framework to address multi-class classification, where a multi-class classifier and multiple binary classifiers are trained together. Moreover, we employ adversarial training to distinguish the class-specific features and the class-agnostic features. The model benefits from better feature representation. We conduct experiments on two large-scale multi-class text classification tasks and demonstrate that the proposed architecture outperforms baseline approaches.
