Non-Autoregressive Neural Machine Translation with Consistency Regularization Optimized Variational Framework

no code implementations • NAACL 2022 • Minghao Zhu, Junli Wang, Chungang Yan

Variational Autoencoder (VAE) is an effective framework to model the interdependency for non-autoregressive neural machine translation (NAT).

Data Augmentation Machine Translation +1

Byzantine-Robust Federated Learning via Credibility Assessment on Non-IID Data

no code implementations • 6 Sep 2021 • Kun Zhai, Qiang Ren, Junli Wang, Chungang Yan

Federated learning is a novel framework that enables resource-constrained edge devices to jointly learn a model, which solves the problem of data protection and data islands.

Anomaly Detection Federated Learning