Grad2Task: Improved Few-shot Text Classification Using Gradients for Task Representation. (arXiv:2201.11576v1 [cs.CL])

Web: http://arxiv.org/abs/2201.11576

Large pretrained language models (LMs) like BERT have improved performance in
many disparate natural language processing (NLP) tasks. However, fine tuning
such models requires a large number of training examples for each target task.
Simultaneously, many realistic NLP problems are "few shot", without a
sufficiently large training set. In this work, we propose a novel conditional
neural process-based approach for few-shot text classification that learns to
transfer from other diverse tasks with rich annotation. Our key idea is to
represent …

arxiv classification representation text text classification