deep-learning
A data augmentation method for NER.
We propose UXLA, a novel data augmentation framework for self-supervised learning in zero-resource transfer learning scenarios.
Data augmentation for low resource tagging.
Adversarial Autoencoder with Cycle Consistency and Improved Training
A demo of malay english Machine translation system.
This paper shows with a semi-supervised algorithm that BLI is more suitable through Non-Linear Mapping (specially for low resource languages).