Entailment as Few-Shot Learner
This addresses the problem of high computational costs for few-shot learning in NLP, offering a more efficient solution for researchers and practitioners, though it builds incrementally on existing entailment and data augmentation techniques.
The paper tackles the challenge of making small language models effective few-shot learners by reformulating NLP tasks as entailment problems, achieving a 12% improvement over existing SOTA methods and competitive performance with models 500 times larger using only 8 examples per task.
Large pre-trained language models (LMs) have demonstrated remarkable ability as few-shot learners. However, their success hinges largely on scaling model parameters to a degree that makes it challenging to train and serve. In this paper, we propose a new approach, named as EFL, that can turn small LMs into better few-shot learners. The key idea of this approach is to reformulate potential NLP task into an entailment one, and then fine-tune the model with as little as 8 examples. We further demonstrate our proposed method can be: (i) naturally combined with an unsupervised contrastive learning-based data augmentation method; (ii) easily extended to multilingual few-shot learning. A systematic evaluation on 18 standard NLP tasks demonstrates that this approach improves the various existing SOTA few-shot learning methods by 12\%, and yields competitive few-shot performance with 500 times larger models, such as GPT-3.