HellaSwag dataset shows state-of-the-art models fail commonsense inference tasks that humans solve easily, built via adversarial filtering of distractors.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2019 2verdicts
UNVERDICTED 2representative citing papers
Hypothesis-only classification reaches 64% accuracy on SNLI, revealing dataset biases in SNLI and MultiNLI that the authors quantify and propose a simple mitigation for.
citing papers explorer
-
HellaSwag: Can a Machine Really Finish Your Sentence?
HellaSwag dataset shows state-of-the-art models fail commonsense inference tasks that humans solve easily, built via adversarial filtering of distractors.
-
Investigating Biases in Textual Entailment Datasets
Hypothesis-only classification reaches 64% accuracy on SNLI, revealing dataset biases in SNLI and MultiNLI that the authors quantify and propose a simple mitigation for.