• Computer Science
  • Published in ArXiv 2019

WINOGRANDE: An Adversarial Winograd Schema Challenge at Scale

@article{Sakaguchi2019WINOGRANDEAA,
  title={WINOGRANDE: An Adversarial Winograd Schema Challenge at Scale},
  author={Keisuke Sakaguchi and Ronan Le Bras and Chandra Bhagavatula and Yejin Choi},
  journal={ArXiv},
  year={2019},
  volume={abs/1907.10641}
}
Highlight Information
The Winograd Schema Challenge (WSC), proposed by Levesque et al. (2011) as an alternative to the Turing Test, was originally designed as a pronoun resolution problem that cannot be solved based on statistical patterns in large text corpora. [...] Key Method Key to our approach is a novel adversarial filtering algorithm AFLITE for systematic bias reduction, combined with a careful crowdsourcing design. Despite the significant increase in training data, the performance of existing state-of-the-art methods remains…Expand Abstract

Citations

Publications citing this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 45 REFERENCES

On the Evaluation of Common-Sense Reasoning in Natural Language Understanding

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Resolving Complex Cases of Definite Pronouns: The Winograd Schema Challenge

VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

Choice of plausible alternatives: An evaluation of commonsense causal reasoning

  • Melissa Roemmele, Cosmin Adrian Bejan, Andrew S Gordon.
  • AAAI Spring Symposium: Logical Formalizations of Commonsense Reasoning, pages 90–95.
  • 2011
VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

The Winograd Schema Challenge

VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Gender Bias in Coreference Resolution

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Language Models are Unsupervised Multitask Learners

VIEW 1 EXCERPT
HIGHLY INFLUENTIAL

Annotation Artifacts in Natural Language Inference Data

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL