JaNLI (Japanese Adversarial Natural Language Inference)
Introduced by Yanaka et al. in Assessing the Generalization Capacity of Pre-trained Language Models through Japanese Adversarial Natural Language Inference
The Japanese Adversarial NLI (JaNLI) dataset is designed to require understanding of Japanese linguistic phenomena and illuminate the vulnerabilities of models. Please see the paper Assessing the Generalization Capacity of Pre-trained Language Models through Japanese Adversarial Natural Language Inference for details.
Papers
| Paper | Code | Results | Date | Stars |
|---|
Dataset Loaders
No data loaders found. You can
submit your data loader here.
No data loaders found. You can
submit your data loader here.
