paper-with-me

홈 › Papers

When does Parameter-Efficient Transfer Learning Work for Machine Translation?

2022-05-23 · Ahmet Üstün, Asa Cooper Stickland

Parameter-efficient fine-tuning methods (PEFTs) offer the promise of adapting large pre-trained models while only tuning a small number of parameters. They have been shown to be competitive with full model fine-tuning for many downstream tasks. However, prior work indicates that PEFTs may not work as well for machine translation (MT), and there is no comprehensive study showing when PEFTs work for MT. We conduct a comprehensive empirical study of PEFTs for MT, considering (1) various parameter budgets, (2) a diverse set of language-pairs, and (3) different pre-trained models. We find that 'adapters', in which small feed-forward networks are added after every layer, are indeed on par with full model fine-tuning when the parameter budget corresponds to 10% of total model parameters. Nevertheless, as the number of tuned parameters decreases, the performance of PEFTs decreases. The magnitude of this decrease depends on the language pair, with PEFTs particularly struggling for distantly related language-pairs. We find that using PEFTs with a larger pre-trained model outperforms full fine-tuning with a smaller model, and for smaller training data sizes, PEFTs outperform full fine-tuning for the same pre-trained model.

📄 PDF Abstract BibTeX arXiv:2205.11277

Code (1)

ahmetustun/fairseq 공식 구현 pytorch

Tasks

Machine Translationparameter-efficient fine-tuningTransfer LearningTranslation

Similar Papers 제목 키워드 기반

When does Parameter-Efficient Transfer Learning Work for Machine Translation?

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

We study parameter-efficient transfer learning methods that adapt a pre-trained model by fine-tuning a small number of parameters, for machine translation. We conduct experiments across a diverse set of languages, compar…

Machine TranslationTransfer LearningTranslation

TransMIA: Membership Inference Attacks Using Transfer Shadow Training

2020-11-30 · Seira Hidano, Takao Murakami, Yusuke Kawamoto

Transfer learning has been widely studied and gained increasing popularity to improve the accuracy of machine learning models by transferring some knowledge acquired in different training. However, no prior work has poin…

BIG-bench Machine LearningTransfer Learning

Robust Policies For Proactive ICU Transfers

2020-02-14 · Julien Grand-Clement, Carri W. Chan, Vineet Goyal, Gabriel Escobar

Patients whose transfer to the Intensive Care Unit (ICU) is unplanned are prone to higher mortality rates than those who were admitted directly to the ICU. Recent advances in machine learning to predict patient deteriora…

Soft Prompt Tuning for Cross-Lingual Transfer: When Less is More

2024-02-06 · Fred Philippy, Siwen Guo, Shohreh Haddadan, Cedric Lothritz 외

Soft Prompt Tuning (SPT) is a parameter-efficient method for adapting pre-trained language models (PLMs) to specific tasks by inserting learnable embeddings, or soft prompts, at the input layer of the PLM, without modify…

Cross-Lingual Transfer

In Neural Machine Translation, What Does Transfer Learning Transfer?

2020-07-01 · ACL 2020 6 · Alham Fikri Aji, Nikolay Bogoychev, Kenneth Heafield, Rico Sennrich

Transfer learning improves quality for low-resource machine translation, but it is unclear what exactly it transfers. We perform several ablation studies that limit information transfer, then measure the quality impact a…

Learning Word EmbeddingsMachine TranslationTransfer LearningTranslation+1