We use cookies to improve your experience with our site.
Gui-Rong Bai, Qing-Bin Liu, Shi-Zhu He, Kang Liu, Jun Zhao. Unsupervised Domain Adaptation on Sentence Matching Through Self-Supervision[J]. Journal of Computer Science and Technology. doi: 10.1007/s11390-022-1479-0
Citation: Gui-Rong Bai, Qing-Bin Liu, Shi-Zhu He, Kang Liu, Jun Zhao. Unsupervised Domain Adaptation on Sentence Matching Through Self-Supervision[J]. Journal of Computer Science and Technology. doi: 10.1007/s11390-022-1479-0

Unsupervised Domain Adaptation on Sentence Matching Through Self-Supervision

  • Although neural approaches have yielded state-of-the-art results in the sentence matching task, the performance of them inevitably drops dramatically when applied to unseen domains. To tackle this cross-domain challenge, we address unsupervised domain adaptation on sentence matching, in which the goal is to have good performance on a target domain with only unlabeled target domain data as well as labeled source domain data. Specifically, we propose to perform self-supervised tasks to achieve it. Different from previous unsupervised domain adaptation methods, self-supervision can not only flexibly suit the characteristics of sentence matching with special design, but also be much easier to optimize. When training, each self-supervised task is performed on both domains simultaneously in an easy-to-hard curriculum, which gradually brings the two domains closer together along the direction relevant to that task. As a result, the classifier trained on the source domain is able to generalize to the unlabeled target domain. In total, we present three types of self-supervised tasks and the results demonstrate the superiority of them. In addition, we further study the performance of different usages of self-supervised tasks, which would inspire how to effectively utilize self-supervision for cross-domain scenarios.
  • loading

Catalog

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return