AdapterHub: A Framework for Adapting Transformers

Jonas Pfeiffer, Andreas Rücklé, Clifton Poth, Aishwarya Kamath, Ivan Vulić, Sebastian Ruder, Kyunghyun Cho, Iryna Gurevych


Abstract
The current modus operandi in NLP involves downloading and fine-tuning pre-trained models consisting of millions or billions of parameters. Storing and sharing such large trained models is expensive, slow, and time-consuming, which impedes progress towards more general and versatile NLP methods that learn from and for many tasks. Adapters—small learnt bottleneck layers inserted within each layer of a pre-trained model— ameliorate this issue by avoiding full fine-tuning of the entire model. However, sharing and integrating adapter layers is not straightforward. We propose AdapterHub, a framework that allows dynamic “stiching-in” of pre-trained adapters for different tasks and languages. The framework, built on top of the popular HuggingFace Transformers library, enables extremely easy and quick adaptations of state-of-the-art pre-trained models (e.g., BERT, RoBERTa, XLM-R) across tasks and languages. Downloading, sharing, and training adapters is as seamless as possible using minimal changes to the training scripts and a specialized infrastructure. Our framework enables scalable and easy access to sharing of task-specific models, particularly in low-resource scenarios. AdapterHub includes all recent adapter architectures and can be found at AdapterHub.ml
Anthology ID:
2020.emnlp-demos.7
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
Month:
October
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
46–54
Language:
URL:
https://aclanthology.org/2020.emnlp-demos.7
DOI:
10.18653/v1/2020.emnlp-demos.7
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-demos.7.pdf
Optional supplementary material:
 2020.emnlp-demos.7.OptionalSupplementaryMaterial.zip