Statements (20)
| Predicate | Object |
|---|---|
| gptkbp:instance_of |
gptkb:benchmark
|
| gptkbp:based_on |
Winograd Schema
|
| gptkbp:challenges |
machine learning models
|
| gptkbp:consists_of |
sentence pairs
|
| gptkbp:developed_by |
gptkb:Winograd_Schema_Challenge
|
| https://www.w3.org/2000/01/rdf-schema#label |
WNLI benchmark
|
| gptkbp:introduced |
gptkb:2018
|
| gptkbp:is_associated_with |
gptkb:Research_Institute
|
| gptkbp:is_compared_to |
other benchmarks
|
| gptkbp:is_designed_to |
test commonsense reasoning
|
| gptkbp:is_evaluated_by |
accuracy
model performance |
| gptkbp:is_implemented_in |
gptkb:Library
|
| gptkbp:is_part_of |
gptkb:GLUE_benchmark
|
| gptkbp:is_related_to |
NLP tasks
|
| gptkbp:is_used_for |
natural language inference
|
| gptkbp:is_utilized_in |
gptkb:physicist
|
| gptkbp:published_by |
academic papers
|
| gptkbp:bfsParent |
gptkb:Tiny_BERT
|
| gptkbp:bfsLayer |
5
|