UMass Amherst & Google Improve Few-Shot Learning on NLP Benchmarks via Task Augmentation and Self-Training | Synced
A team from University of Massachusetts Amherst and Google Research proposes STraTA, an approach that combines task augmentation and self-training to leverage unlabelled data and improve sample eff...
Source: Synced | AI Technology & Industry Review
A team from University of Massachusetts Amherst and Google Research proposes STraTA, an approach that combines task augmentation and self-training to leverage unlabelled data and improve sample efficiency and performance on NLP tasks.