@inproceedings{wu-etal-2021-conditional,
    title = "Conditional Adversarial Networks for Multi-Domain Text Classification",
    author = "Wu, Yuan  and
      Inkpen, Diana  and
      El-Roby, Ahmed",
    editor = "Ben-David, Eyal  and
      Cohen, Shay  and
      McDonald, Ryan  and
      Plank, Barbara  and
      Reichart, Roi  and
      Rotman, Guy  and
      Ziser, Yftah",
    booktitle = "Proceedings of the Second Workshop on Domain Adaptation for NLP",
    month = apr,
    year = "2021",
    address = "Kyiv, Ukraine",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2021.adaptnlp-1.3/",
    pages = "16--27",
    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 stronger discriminability to the learned features, for multi-domain text classification (MDTC). The proposed CAN introduces a conditional domain discriminator to model the domain variance in both the shared feature representations and the 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."
}