HiddenCut: Simple Data Augmentation for Natural Language Understanding with Better Generalization
This addresses generalization issues in NLP for practitioners using pre-trained models, though it is incremental as it builds on existing augmentation methods.
The paper tackles the problem of poor generalization in fine-tuned NLP models by proposing HiddenCut, a data augmentation technique that drops contiguous spans in hidden space during training, resulting in state-of-the-art performance on the GLUE benchmark and improved out-of-distribution generalization.
Fine-tuning large pre-trained models with task-specific data has achieved great success in NLP. However, it has been demonstrated that the majority of information within the self-attention networks is redundant and not utilized effectively during the fine-tuning stage. This leads to inferior results when generalizing the obtained models to out-of-domain distributions. To this end, we propose a simple yet effective data augmentation technique, HiddenCut, to better regularize the model and encourage it to learn more generalizable features. Specifically, contiguous spans within the hidden space are dynamically and strategically dropped during training. Experiments show that our HiddenCut method outperforms the state-of-the-art augmentation methods on the GLUE benchmark, and consistently exhibits superior generalization performances on out-of-distribution and challenging counterexamples. We have publicly released our code at https://github.com/GT-SALT/HiddenCut.