@inproceedings{li-zhang-2021-semi,
    title = "Semi-supervised Meta-learning for Cross-domain Few-shot Intent Classification",
    author = "Li, Yue  and
      Zhang, Jiong",
    editor = "Lee, Hung-Yi  and
      Mohtarami, Mitra  and
      Li, Shang-Wen  and
      Jin, Di  and
      Korpusik, Mandy  and
      Dong, Shuyan  and
      Vu, Ngoc Thang  and
      Hakkani-Tur, Dilek",
    booktitle = "Proceedings of the 1st Workshop on Meta Learning and Its Applications to Natural Language Processing",
    month = aug,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2021.metanlp-1.8/",
    doi = "10.18653/v1/2021.metanlp-1.8",
    pages = "67--75",
    abstract = "Meta learning aims to optimize the model{'}s capability to generalize to new tasks and domains. Lacking a data-efficient way to create meta training tasks has prevented the application of meta-learning to the real-world few shot learning scenarios. Recent studies have proposed unsupervised approaches to create meta-training tasks from unlabeled data for free, e.g., the SMLMT method (Bansal et al., 2020a) constructs unsupervised multi-class classification tasks from the unlabeled text by randomly masking words in the sentence and let the meta learner choose which word to fill in the blank. This study proposes a semi-supervised meta-learning approach that incorporates both the representation power of large pre-trained language models and the generalization capability of prototypical networks enhanced by SMLMT. The semi-supervised meta training approach avoids overfitting prototypical networks on a small number of labeled training examples and quickly learns cross-domain task-specific representation only from a few supporting examples. By incorporating SMLMT with prototypical networks, the meta learner generalizes better to unseen domains and gains higher accuracy on out-of-scope examples without the heavy lifting of pre-training. We observe significant improvement in few-shot generalization after training only a few epochs on the intent classification tasks evaluated in a multi-domain setting."
}