AdapterHub Playground: Simple and Flexible Few-Shot Learning with Adapters

TL;DR

AdapterHub Playground is an accessible tool that enables users to perform few-shot learning and adapt pretrained language models for NLP tasks without coding, enhancing usability and performance.

Contribution

It introduces an intuitive interface for leveraging adapters in NLP, simplifying model adaptation and demonstrating improved few-shot learning performance.

Findings

Performance increases in few-shot learning scenarios

User study confirms high usability and accessibility

Prototypical use-cases showcase versatility of the tool

Abstract

The open-access dissemination of pretrained language models through online repositories has led to a democratization of state-of-the-art natural language processing (NLP) research. This also allows people outside of NLP to use such models and adapt them to specific use-cases. However, a certain amount of technical proficiency is still required which is an entry barrier for users who want to apply these models to a certain task but lack the necessary knowledge or resources. In this work, we aim to overcome this gap by providing a tool which allows researchers to leverage pretrained models without writing a single line of code. Built upon the parameter-efficient adapter modules for transfer learning, our AdapterHub Playground provides an intuitive interface, allowing the usage of adapters for prediction, training and analysis of textual data for a variety of NLP tasks. We present the tool's architecture and demonstrate its advantages with prototypical use-cases, where we show that predictive performance can easily be increased in a few-shot learning scenario. Finally, we evaluate its usability in a user study. We provide the code and a live interface at https://adapter-hub.github.io/playground.