Original paper
Few-Shot Text Generation with Natural Language Instructions
Published: Jan 1, 2021
Abstract
Providing pretrained language models with simple task descriptions in natural language enables them to solve some tasks in a fully unsupervised fashion. Moreover, when combined with regular learning from examples, this idea yields impressive few-shot results for a wide range of text classification tasks. It is also a promising direction to improve data efficiency in generative settings, but there are several challenges to using a combination of...
Paper Details
Title
Few-Shot Text Generation with Natural Language Instructions
Published Date
Jan 1, 2021