150D Multiway Attention Network Ensemble

Reported on 2 benchmarks across 1 task

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

Natural Language Processing2 results

Natural Language InferenceonSNLI
% Test Accuracy
89.4
best: 94.7 (UnitedSynT5 (3B))
Natural Language InferenceonSNLI
% Train Accuracy
95.5
best: 99.7 (+ Unigram and bigram features)