Out of Distribution
Related Papers
Types of Out-of-Distribution Texts and How to Detect Them
AbstractDespite agreement on the importance of detecting out-of-distribution (OOD) examples, there is little consensus on the formal definition of the distribution shifts of OOD examples and how to best detect …...
On Curriculum Learning for Commonsense Reasoning
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. …...
Training Dynamics for Curriculum Learning: A Study on Monolingual and Cross-lingual NLU
AbstractCurriculum Learning (CL) is a technique of training models via ranking examples in a typically increasing difficulty trend with the aim of accelerating convergence and improving generalisability. Current approaches for …...
Extracting Victim Counts from Text
AbstractDecision-makers in the humanitarian sector rely on timely and exact information during crisis events. Knowing how many civilians were injured during an earthquake is vital to allocate aids properly. Information …...
Probing Out-of-Distribution Robustness of Language Models with Parameter-Efficient Transfer Learning
AbstractAs the size of the pre-trained language model (PLM) continues to increase, numerous parameter-efficient transfer learning methods have been proposed recently to compensate for the high cost of fine-tuning. While …...