Towards robust natural language and image processing In low-resource scenarios

Abstract

Comparison of the representations obtained at each layer before (Base) and after adapter-based tuning or fine-tuning on BERT-base using Representational Similarity Analysis (RSA). . . . . . . . . 4.3 Test performance w.r.t the number of training examples. Reported results are averages across five runs with different random seeds. . 4.4 Box plots of test performance distribution over 20 runs across different learning rates.