paper-with-me

홈 › Papers

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

2021-08-18 · ACL 2022 5 · Tilman Beck, Bela Bohlender, Christina Viehmann, Vincent Hane, Yanik Adamson, Jaber Khuri, Jonas Brossmann, Jonas Pfeiffer, Iryna Gurevych

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.

📄 PDF Abstract BibTeX arXiv:2108.08103

Code (1)

adapter-hub/playground 공식 구현

Tasks

Few-Shot LearningTransfer Learning

Methods 이 논문이 사용한 방법론

Adapter 설명 없음

Similar Papers 제목 키워드 기반

Adapters: A Unified Library for Parameter-Efficient and Modular Transfer Learning

2023-11-18 · Clifton Poth, Hannah Sterz, Indraneil Paul, Sukannya Purkayastha 외

We introduce Adapters, an open-source library that unifies parameter-efficient and modular transfer learning in large language models. By integrating 10 diverse adapter methods into a unified interface, Adapters offers e…

Transfer Learning

AdapterHub: A Framework for Adapting Transformers

2020-07-15 · EMNLP 2020 11 · Jonas Pfeiffer, Andreas Rücklé, Clifton Poth, Aishwarya Kamath 외

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-consu…

XLM-R

MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer

2020-04-30 · EMNLP 2020 11 · Jonas Pfeiffer, Ivan Vulić, Iryna Gurevych, Sebastian Ruder

The main goal behind state-of-the-art pre-trained multilingual models such as multilingual BERT and XLM-R is enabling and bootstrapping NLP applications in low-resource languages through zero-shot or few-shot cross-lingu…

Cross-Lingual Transfernamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+2

AdapterFusion: Non-Destructive Task Composition for Transfer Learning

2020-05-01 · EACL 2021 2 · Jonas Pfeiffer, Aishwarya Kamath, Andreas Rücklé, Kyunghyun Cho 외

Sequential fine-tuning and multi-task learning are methods aiming to incorporate knowledge from multiple tasks; however, they suffer from catastrophic forgetting and difficulties in dataset balancing. To address these sh…

Language ModellingMulti-Task LearningTransfer Learning

Surprisingly Simple Adapter Ensembling for Zero-Shot Cross-Lingual Sequence Tagging

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Adapters are parameter-efficient modules added to pretrained Transformer models that facilitate cross-lingual transfer. Language adapters and task adapters can be separately trained and zero-shot transfer is enabled by p…

Cross-Lingual Transfernamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)+3