Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Natural Language Inference on adv-MNLI TextFooler-RoBERTa
Loading...
65.6
Accuracy (Matched)
InfoBERT
23.272
34.261
45.25
56.239
Oct 5, 2020
Accuracy (Matched)
Accuracy (Mismatched)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy (Matched)
Accuracy (Mismatched)
InfoBERT
Training=Adversarial T...
2020.10
65.6
67.3
FreeLB
Training=Adversarial T...
2020.10
64
62.9
InfoBERT
Training=Standard Trai...
2020.10
57.2
58.6
Vanilla
Training=Standard Trai...
2020.10
57
57.5
InfoBERT
Training=Adversarial T...
2020.10
56.9
55.5
InfoBERT
Training=Standard Trai...
2020.10
50.3
52.1
FreeLB
Training=Adversarial T...
2020.10
49.5
50.6
Vanilla
Training=Standard Trai...
2020.10
24.9
24.9
Feedback
Search any
task
Search any
task
