@inproceedings{li-etal-2018-whats,
    title = "What{'}s in a Domain? Learning Domain-Robust Text Representations using Adversarial Training",
    author = "Li, Yitong  and
      Baldwin, Timothy  and
      Cohn, Trevor",
    editor = "Walker, Marilyn  and
      Ji, Heng  and
      Stent, Amanda",
    booktitle = "Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)",
    month = jun,
    year = "2018",
    address = "New Orleans, Louisiana",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/N18-2076/",
    doi = "10.18653/v1/N18-2076",
    pages = "474--479",
    abstract = "Most real world language problems require learning from heterogenous corpora, raising the problem of learning robust models which generalise well to both similar (\textit{in domain}) and dissimilar (\textit{out of domain}) instances to those seen in training. This requires learning an underlying task, while not learning irrelevant signals and biases specific to individual domains. We propose a novel method to optimise both in- and out-of-domain accuracy based on joint learning of a structured neural model with domain-specific and domain-general components, coupled with adversarial training for domain. Evaluating on multi-domain language identification and multi-domain sentiment analysis, we show substantial improvements over standard domain adaptation techniques, and domain-adversarial training."
}