Statements (59)
| Predicate | Object |
|---|---|
| gptkbp:instance_of |
gptkb:Performance_Monitoring
|
| gptkbp:challenges |
deep learning models
|
| gptkbp:consists_of |
sentence pairs
|
| gptkbp:contains |
test set
validation set |
| gptkbp:designed_for |
natural language inference
|
| gptkbp:developed_by |
gptkb:Allen_Institute_for_AI
|
| gptkbp:evaluates |
model performance
|
| https://www.w3.org/2000/01/rdf-schema#label |
MNLI benchmark
|
| gptkbp:includes |
multi-genre data
|
| gptkbp:is_based_on |
SNLI dataset
|
| gptkbp:is_cited_in |
research papers
theses academic articles dissertations |
| gptkbp:is_documented_in |
neutral
labels contradiction entailment |
| gptkbp:is_evaluated_by |
gptkb:historical_memory
F1 score accuracy cross-validation precision holdout testing k-fold validation |
| gptkbp:is_influential_in |
gptkb:AI_technology
cognitive science NLP advancements |
| gptkbp:is_part_of |
gptkb:GLUE_benchmark
evaluation frameworks NLP benchmarks AI benchmarks |
| gptkbp:is_popular_in |
NLP community
|
| gptkbp:is_related_to |
gptkb:GPT-3
gptkb:BERT gptkb:T5 gptkb:Ro_BERTa gptkb:XLNet pre-trained models fine-tuning text classification language understanding semantic similarity transfer learning techniques |
| gptkbp:is_supported_by |
universities
research institutions open-source libraries |
| gptkbp:is_used_for |
algorithm comparison
system evaluation model benchmarking |
| gptkbp:is_used_in |
gptkb:challenges
competitions machine learning research |
| gptkbp:provides |
evaluation metrics
|
| gptkbp:released_in |
gptkb:2017
|
| gptkbp:supports |
transfer learning
|
| gptkbp:bfsParent |
gptkb:Ford_Model_T
|
| gptkbp:bfsLayer |
4
|