Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Semantic Textual Similarity on STS-15
Loading...
0.7492
Spearman's Rho
BERTlarge-flow (target)
0.353584
0.456292
0.559
0.661708
Nov 2, 2020
Spearman's Rho
Updated 4d ago
Evaluation Results
Method
Method
Links
Spearman's Rho
BERTlarge-flow (target)
Backbone=BERT-large, P...
2020.11
0.7492
BERTlarge-flow (NLI*)
Backbone=BERT-large, P...
2020.11
0.7487
BERTbase-flow (target)
Backbone=BERT-base, Po...
2020.11
0.7377
BERTbase-flow (NLI*)
Backbone=BERT-base, Po...
2020.11
0.7292
BERTbase-last2avg
Backbone=BERT-base, Po...
2020.11
0.7095
Avg. GloVe embeddings
Backbone=GloVe, Poolin...
2020.11
0.6825
BERTlarge-last2avg
Backbone=BERT-large, P...
2020.11
0.6804
Avg. BERT embeddings
Backbone=BERT, Pooling...
2020.11
0.6315
BERTbase
Backbone=BERT-base, Po...
2020.11
0.6275
BERTlarge
Backbone=BERT-large, P...
2020.11
0.5654
BERT CLS-vector
Backbone=BERT, Pooling...
2020.11
0.3688
Feedback
Search any
task
Search any
task