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.- Anthology ID:
- 2021.repl4nlp-1.11
- Volume:
- Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Editors:
- Anna Rogers, Iacer Calixto, Ivan Vulić, Naomi Saphra, Nora Kassner, Oana-Maria Camburu, Trapit Bansal, Vered Shwartz
- Venue:
- RepL4NLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 90–99
- Language:
- URL:
- https://aclanthology.org/2021.repl4nlp-1.11
- DOI:
- 10.18653/v1/2021.repl4nlp-1.11
- Cite (ACL):
- Seungwon Kim, Alex Shum, Nathan Susanj, and Jonathan Hilgart. 2021. Revisiting Pretraining with Adapters. In Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021), pages 90–99, Online. Association for Computational Linguistics.
- Cite (Informal):
- Revisiting Pretraining with Adapters (Kim et al., RepL4NLP 2021)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2021.repl4nlp-1.11.pdf
- Data
- AG News, IMDb Movie Reviews, SciERC