Conditional Adversarial Networks for Multi-Domain Text Classification
This work addresses multi-domain text classification, an incremental improvement for natural language processing applications.
The paper tackles multi-domain text classification by proposing conditional adversarial networks (CANs) to enhance shared feature discriminability, achieving improved performance over prior methods on two benchmarks and demonstrating generalization to unseen domains.
In this paper, we propose conditional adversarial networks (CANs), a framework that explores the relationship between the shared features and the label predictions to impose more discriminability to the shared features, for multi-domain text classification (MDTC). The proposed CAN introduces a conditional domain discriminator to model the domain variance in both shared feature representations and class-aware information simultaneously and adopts entropy conditioning to guarantee the transferability of the shared features. We provide theoretical analysis for the CAN framework, showing that CAN's objective is equivalent to minimizing the total divergence among multiple joint distributions of shared features and label predictions. Therefore, CAN is a theoretically sound adversarial network that discriminates over multiple distributions. Evaluation results on two MDTC benchmarks show that CAN outperforms prior methods. Further experiments demonstrate that CAN has a good ability to generalize learned knowledge to unseen domains.