Атакающие наборы данных

AbstractPhenomenon-specific “adversarial” datasets have been recently designed to perform targeted stress-tests for particular inference types. Recent work (Liu et al., 2019a) proposed that such datasets can be utilized for training …...

AbstractDespite the advances in Natural Language Inference through the training of massive deep models, recent work has revealed the generalization difficulties of such models, which fail to perform on adversarial …...

AbstractCurrent textual question answering (QA) models achieve strong performance on in-domain test sets, but often do so by fitting surface-level patterns, so they fail to generalize to out-of-distribution settings. To …...