Conversation disentanglement aims to group utterances into detached sessions, which is a fundamental task in processing multi-party conversations.
Few-shot text classification is a fundamental NLP task in which a model aims to classify text into a large number of categories, given only a few training examples per category.
Traditional data augmentation aims to increase the coverage of the input distribution by generating augmented examples that strongly resemble original samples in an online fashion where augmented examples dominate training.
We present COVID-Q, a set of 1, 690 questions about COVID-19 from 13 sources, which we annotate into 15 question categories and 207 question clusters.
Specifically, both ShrinkCNN and ShrinkRNN are crafted within 1. 5 GPU hours, which is 7. 2x and 6. 7x faster than the crafting time of SOTA CNN and RNN models, respectively.