Repository logo
 

AdapterHub: A Framework for Adapting Transformers

Published version
Peer-reviewed

Type

Conference Object

Change log

Authors

Pfeiffer, Jonas 
Ruckle, Andreas 
Poth, Clifton 
Kamath, Aishwarya 
Vulic, Ivan 

Abstract

The current modus operandi in NLP involves downloading and fine-tuning pre-trained models consisting of hundreds of millions, or even 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.

Description

Keywords

Journal Title

Proceedings of the Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP 2020)

Conference Name

Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP 2020)

Journal ISSN

Volume Title

Publisher

Association for Computational Linguistics

Rights

All rights reserved
Sponsorship
European Research Council (648909)