Learning to Few-Shot Learn Across Diverse Natural Language Classification Tasks

Understand

Self-supervised pre-training of transformer models has shown enormous success in improving performance on a number of downstream tasks.

• However, fine-tuning on a new task still requires large amounts of task-specific labelled data to achieve good performance.
• We consider this problem of learning to generalize to new tasks with few examples as a meta-learning problem.
• While meta-learning has shown tremendous progress in recent years, its application is still limited to simulated problems or problems with limited diversity across tasks.