aESIM

Reported on 4 benchmarks across 1 task · 1 paper · 1 SOTA

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

Natural Language Processing4 results

Natural Language InferenceonQuora Question Pairs
Accuracy· 2018-12-05
88.01
SOTA
Attention Boosted Sequential Inference Model arXiv:1812.01840
Natural Language InferenceonSNLI
% Test Accuracy· 2018-12-05
88.1
best: 94.7 (UnitedSynT5 (3B))
Attention Boosted Sequential Inference Model arXiv:1812.01840
Natural Language InferenceonMultiNLI
Matched· 2018-12-05
73.9
best: 92.6 (Turing NLR v5 XXL 5.4B (fine-tuned))
Attention Boosted Sequential Inference Model arXiv:1812.01840
Natural Language InferenceonMultiNLI
Mismatched· 2018-12-05
73.9
best: 92.4 (Turing NLR v5 XXL 5.4B (fine-tuned))
Attention Boosted Sequential Inference Model arXiv:1812.01840