Bibliography (7):

1. T5: Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

2. mT5: A massively multilingual pre-trained text-to-text transformer

3. GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding

4. TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension

5. SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems

6. Attention Is All You Need

7. https://arxiv.org/pdf/2101.03961.pdf#page=18&org=google