SICK

SICK is a dataset for recognizing textual entailment (RTE), containing 4.5K/0.5K/5.0K train/dev/test examples. Each example consists of a hypothesis and a premise, and the goal is to determine if the premise is entailed by, contradicts, or is neutral to the hypothesis.

Data and Resources

Cite this as

Jamie Ryan Kiros, Yukun Zhu, Richard S. Zemel, Ruslan Salakhutdinov, Raquel Urtasun, Antonio Torralba, Sanja Fidler (2024). Dataset: SICK. https://doi.org/10.57702/arwr3woh

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2103.05135
Citation
  • https://doi.org/10.48550/arXiv.2201.04467
  • https://doi.org/10.48550/arXiv.1904.02464
  • https://doi.org/10.1145/3178876.3186022
  • https://doi.org/10.48550/arXiv.2304.04726
  • https://doi.org/10.48550/arXiv.1702.02171
  • https://doi.org/10.48550/arXiv.1904.12166
  • https://doi.org/10.48550/arXiv.1706.03146
Author Jamie Ryan Kiros
More Authors
Yukun Zhu
Richard S. Zemel
Ruslan Salakhutdinov
Raquel Urtasun
Antonio Torralba
Sanja Fidler
Homepage https://www.aclweb.org/anthology/D15-1012