Textual Task Formulation
Connor and Yannic discuss the idea of formulating tasks as text for models like GPT-2, exploring the potential for meta learning and pointer networks in NLP. The conversation delves into the concept of context-free question answering and the effectiveness of pre-training models like GPT-2.In this clip
From this podcast
Machine Learning Street Talk (MLST)
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Related Questions