@inproceedings{kim-etal-2021-revisiting,
    title = "Revisiting Pretraining with Adapters",
    author = "Kim, Seungwon  and
      Shum, Alex  and
      Susanj, Nathan  and
      Hilgart, Jonathan",
    editor = "Rogers, Anna  and
      Calixto, Iacer  and
      Vuli{\'c}, Ivan  and
      Saphra, Naomi  and
      Kassner, Nora  and
      Camburu, Oana-Maria  and
      Bansal, Trapit  and
      Shwartz, Vered",
    booktitle = "Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)",
    month = aug,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/moar-dois/2021.repl4nlp-1.11/",
    doi = "10.18653/v1/2021.repl4nlp-1.11",
    pages = "90--99",
    abstract = "Pretrained language models have served as the backbone for many state-of-the-art NLP results. These models are large and expensive to train. Recent work suggests that continued pretraining on task-specific data is worth the effort as pretraining leads to improved performance on downstream tasks. We explore alternatives to full-scale task-specific pretraining of language models through the use of adapter modules, a parameter-efficient approach to transfer learning. We find that adapter-based pretraining is able to achieve comparable results to task-specific pretraining while using a fraction of the overall trainable parameters. We further explore direct use of adapters without pretraining and find that the direct fine-tuning performs mostly on par with pretrained adapter models, contradicting previously proposed benefits of continual pretraining in full pretraining fine-tuning strategies. Lastly, we perform an ablation study on task-adaptive pretraining to investigate how different hyperparameter settings can change the effectiveness of the pretraining."
}