Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

<b>Uncertainty-Aware Bayesian Federated Learning for Low-Resource Neural Machine Translation at the Edge</b>

Domaine:

natural language processing

Type de record:

paper
Créateur:
Na
Éditeur:
fig
Hôte:avatar
Edge translation systems must balance limited computation, data locality, and weak performance on low-resource language pairs. This study presents Multitask Bayesian Federated Learning (MT-BayesFL), a multilingual translation framework that combines a lightweight shared encoder, task-specific decoders, matrix-normal posteriors over shared attention projections, and covariance-aware server aggregation.

Visit

doi.org

Tasks

machine translation

Tags

Applied computing not elsewhere classified

Licenses

Creative Commons Attribution 4.0 Internationalhttps://creativecommons.org/licenses/by/4.0/legalcode

Similaires

Optimizing Uncertainty-Aware Deep Learning for On-the-Edge Murmur Detection in Low-Resource SettingsTrivial Transfer Learning for Low-Resource Neural Machine TranslationMultitask Bayesian Federated Learning for Privacy-Preserving English Translation Model Training Across Edge DevicesUnsupervised Neural Machine Translation for Low-Resource Domains via Meta-LearningData Augmentation for Low-Resource Neural Machine TranslationMultilingual Neural Machine Translation for Low Resource Languages

Optimizing Uncertainty-Aware Deep Learning for On-the-Edge Murmur Detection in Low-Resource Settings

Early and reliable detection of heart murmurs is essential for the timely diagnosis of cardiovascula

Trivial Transfer Learning for Low-Resource Neural Machine Translation

Transfer learning has been proven as an effective technique for neural machine translation under low

Multitask Bayesian Federated Learning for Privacy-Preserving English Translation Model Training Across Edge Devices

To address core challenges such as resource constraints on edge devices, data privacy concerns, and

Unsupervised Neural Machine Translation for Low-Resource Domains via Meta-Learning

Unsupervised machine translation, which utilizes unpaired monolingual corpora as training data, has

Data Augmentation for Low-Resource Neural Machine Translation

The quality of a Neural Machine Translation system depends substantially on the availability of siza

Multilingual Neural Machine Translation for Low Resource Languages

Neural Machine Translation (NMT) has been shown to be more effective in translation tasks compared t