“DART: Differentiable Prompt Makes Pre-Trained Language Models Better Few-Shot Learners”, 2021-08-30 (; backlinks; similar):
Large-scale pre-trained language models have contributed to natural language processing by demonstrating remarkable abilities as few-shot learners. However, their effectiveness depends mainly on scaling the model parameters and prompt design, hindering their implementation in most real-world applications. This study proposes a novel pluggable, extensible, and efficient approach named DifferentiAble pRompT (DART), which can convert small language models into better few-shot learners without any prompt engineering.
The main principle behind this approach involves reformulating potential natural language processing tasks into the task of a pre-trained language model and differentially optimizing the prompt template as well as the target label with backpropagation. Furthermore, the proposed approach can be: (1) Plugged to any pre-trained language models; (2) Extended to widespread classification tasks.
A comprehensive evaluation of standard NLP tasks demonstrates that the proposed approach achieves a better few-shot performance.
Code is available in Github.