Adversarial Multi-Binary Neural Network for Multi-class Classification
This work addresses multi-class text classification, a key problem in NLP, by enhancing feature representation through adversarial training, but it appears incremental as it builds on existing multi-task and adversarial approaches.
The paper tackled multi-class text classification by training a multi-class classifier alongside multiple binary classifiers within a multi-task framework, using adversarial training to separate class-specific and class-agnostic features, resulting in improved performance over baseline methods on two large-scale datasets.
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.