• Computer Science
• Published in EMNLP/IJCNLP 2019
• DOI:10.18653/v1/d19-1608

QuaRTz: An Open-Domain Dataset of Qualitative Relationship Questions

@inproceedings{Tafjord2019QuaRTzAO,
  title={QuaRTz: An Open-Domain Dataset of Qualitative Relationship Questions},
  author={Oyvind Tafjord and Matt Gardner and Kevin Lin and Peter Clark},
  booktitle={EMNLP/IJCNLP},
  year={2019}
}

• Oyvind Tafjord, Matt Gardner, +1 author Peter Clark

We introduce the first open-domain dataset, called QuaRTz, for reasoning about textual qualitative relationships. QuaRTz contains general qualitative statements, e.g., "A sunscreen with a higher SPF protects the skin longer.", twinned with 3864 crowdsourced situated questions, e.g., "Billy is wearing sunscreen with a lower SPF than Lucy. Who will be best protected from the sun?", plus annotations of the properties being compared. Unlike previous datasets, the general knowledge is textual and… CONTINUE READING

View PDF on ArXiv

Save to Library

Create Alert

Cite