1 |
Delving Deeper into Cross-lingual Visual Question Answering ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Smelting Gold and Silver for Improved Multilingual AMR-to-Text Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Smelting Gold and Silver for Improved Multilingual AMR-to-Text Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
UNKs Everywhere: Adapting Multilingual Language Models to New Scripts ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
UNKs Everywhere: Adapting Multilingual Language Models to New Scripts ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer
|
|
|
|
BASE
|
|
Show details
|
|
13 |
AdapterHub: A Framework for Adapting Transformers
|
|
Pfeiffer, Jonas; Ruckle, Andreas; Poth, Clifton; Kamath, Aishwarya; Vulic, Ivan; Ruder, Sebastian; Cho, Kyunghyun; Gurevych, Iryna. - : Association for Computational Linguistics, 2020. : Proceedings of the Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP 2020), 2020
|
|
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.
|
|
URL: https://doi.org/10.17863/CAM.62205 https://www.repository.cam.ac.uk/handle/1810/315098
|
|
BASE
|
|
Hide details
|
|
14 |
Specialising Distributional Vectors of All Words for Lexical Entailment ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Specializing distributional vectors of all words for lexical entailment
|
|
|
|
BASE
|
|
Show details
|
|
16 |
A neural autoencoder approach for document ranking and query refinement in pharmacogenomic information retrieval
|
|
|
|
BASE
|
|
Show details
|
|
|
|