Conditional Adversarial Networks for Multi-Domain Text Classification

Abstract

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.

The Second Workshop on Domain Adaptation for NLP at EACL2021

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• Conditional Generative Adversarial Nets
• How transferable are features in deep neural networks?
• Domain Separation Networks
• A Convex Formulation for Learning Task Relationships in Multi-Task Learning
• Multiple Source Domain Adaptation with Adversarial Training of Neural Networks