HellaSwag

AbstractRecent work by Zellers et al. (2018) introduced a new task of commonsense natural language inference: given an event description such as “A woman sits at a piano,” a machine …...

AbstractFine-tuning of pre-trained transformer models has become the standard approach for solving common NLP tasks. Most of the existing approaches rely on a randomly initialized classifier on top of such …...

AbstractCommonsense reasoning tasks follow a standard paradigm of finetuning pretrained language models on the target task data, where samples are introduced to the model in a random order during training. …...

AbstractData Augmentation (DA) is known to improve the generalizability of deep neural networks. Most existing DA techniques naively add a certain number of augmented samples without considering the quality and …...