Snorkel MeTaL(ensemble)

Reported on 5 benchmarks across 3 tasks · 1 paper · 5 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing5 results

Semantic Textual SimilarityonQuora Question Pairs
Accuracy· 2018-10-05
89.9
best: 92.4 (data2vec)
SOTA
Training Complex Models with Multi-Task Weak Supervision arXiv:1810.02840
Semantic Textual SimilarityonQuora Question Pairs
F1· 2018-10-05
73.1
best: 90.7 (ALICE)
SOTA
Training Complex Models with Multi-Task Weak Supervision arXiv:1810.02840
Sentiment AnalysisonSST-2 Binary classification
Accuracy· 2018-10-05
96.2
best: 97.5 (T5-11B)
SOTA
Training Complex Models with Multi-Task Weak Supervision arXiv:1810.02840
Paraphrase IdentificationonQuora Question Pairs
Accuracy· 2018-10-05
89.9
best: 92.4 (data2vec)
SOTA
Training Complex Models with Multi-Task Weak Supervision arXiv:1810.02840
Paraphrase IdentificationonQuora Question Pairs
F1· 2018-10-05
73.1
best: 90.7 (ALICE)
SOTA
Training Complex Models with Multi-Task Weak Supervision arXiv:1810.02840