A2R2: Robust Unsupervised Neural Machine Translation With Adversarial Attack and Regularization on Representations

A2R2: Robust Unsupervised Neural Machine Translation With Adversarial Attack and Regularization on Representations

Unsupervised neural machine translation (UNMT) has recently achieved significant progress without requirement on any parallel data. The models for UNMT are typically the sequence-to-sequence architecture with an encoder to map sentences in different languages to a shared latent space, and a decoder...

Full description

Bibliographic Details
Main Authors: Heng Yu, Haoran Luo, Yuqi Yi, Fan Cheng
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
Natural language processing
machine translation
unsupervised learning
adversarial attack
Online Access:https://ieeexplore.ieee.org/document/9336722/

Internet

https://ieeexplore.ieee.org/document/9336722/

Similar Items