pith. sign in

Title resolution pending

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CL 2

years

2019 2

verdicts

UNVERDICTED 2

representative citing papers

Investigating Biases in Textual Entailment Datasets

cs.CL · 2019-06-23 · unverdicted · novelty 5.0

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

Showing 2 of 2 citing papers.

  • HellaSwag: Can a Machine Really Finish Your Sentence? cs.CL · 2019-05-19 · unverdicted · none · ref 2

    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 cs.CL · 2019-06-23 · unverdicted · none · ref 4

    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.