Simple is Better! Lightweight Data Augmentation for Low Resource Slot Filling and Intent Classification
This addresses the problem of expensive data creation for new domains in NLP, offering a practical solution for low-resource settings, though it is incremental compared to more complex methods.
The paper tackles data scarcity in slot filling and intent classification by proposing lightweight data augmentation methods, which achieve significant performance improvements on ATIS and SNIPS datasets and enhance BERT-based models.
Neural-based models have achieved outstanding performance on slot filling and intent classification, when fairly large in-domain training data are available. However, as new domains are frequently added, creating sizeable data is expensive. We show that lightweight augmentation, a set of augmentation methods involving word span and sentence level operations, alleviates data scarcity problems. Our experiments on limited data settings show that lightweight augmentation yields significant performance improvement on slot filling on the ATIS and SNIPS datasets, and achieves competitive performance with respect to more complex, state-of-the-art, augmentation approaches. Furthermore, lightweight augmentation is also beneficial when combined with pre-trained LM-based models, as it improves BERT-based joint intent and slot filling models.