WNLI
Winograd NLI
The WNLI dataset is a part of the GLUE benchmark used for Natural Language Inference (NLI).
How to run
$ npm i -g lettokenburn-cli$ ltb bench info wnli
External harness. No Harbor adapter has been generated for this benchmark yet. `ltb bench info` prints the known links.
Runs happen on your machine with your own subscription; only the score summary is pushed. CLI docs
Scores
2 sourced entries| Harness | Source | Confidence | Link | |||
|---|---|---|---|---|---|---|
| T5-XXL 11B | 93.2 | N/A | Independent | medium | Oct 23, 2019 | arxiv.org |
| ERNIE 2.0 Large | 67.8 | N/A | Independent | medium | Jul 29, 2019 | arxiv.org |
Every number links to where it was published. Low-confidence rows are muted and need per-cell verification.
Reproduced by the community
All runsAbout
The WNLI dataset is a part of the GLUE benchmark used for Natural Language Inference (NLI). It contains pairs of sentences, and the task is to determine whether the second sentence is an entailment of the first one or not. The dataset is used to train and evaluate models on their ability to understand these relationships between sentences.