Loading...
Loading...
Available on 1 platform
Sign in to view source links and access this dataset
ZEST is a benchmark for zero-shot generalization to unseen NLP tasks, created by the Allen Institute for AI. It contains 25,000 labeled instances distributed across 1,251 different tasks. The dataset is hosted on AWS Open Data and is licensed under CC-BY-4.0.
Data is hosted on S3; users must have appropriate AWS tools or credentials for access.