pair-classification text
CTKFactsNLI
Czech Natural Language Inference dataset of around 3K evidence-claim pairs labelled with SUPPORTS, REFUTES or NOT ENOUGH INFO veracity labels. Extracted from a round of fact-checking experiments.
Domains: NewsWritten
Languages: Czech
- Task type
- PairClassification
- Main metric
max_ap- Reference
- https://arxiv.org/abs/2201.11115
- Source dataset
- mteb/CTKFactsNLI
- License
- cc-by-sa-3.0
- Dates
- 2020-09-01 → 2021-08-31
- Annotations
- human-annotated
- Sample creation
- found
Models scored …