300D Reinforced Self-Attention Network

Reported on 2 benchmarks across 1 task · 1 paper

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· 2018-01-31
86.3
best: 94.7 (UnitedSynT5 (3B))
Reinforced Self-Attention Network: a Hybrid of Hard and Soft Attention for Sequence Modeling arXiv:1801.10296
Natural Language InferenceonSNLI
% Train Accuracy· 2018-01-31
92.6
best: 99.7 (+ Unigram and bigram features)
Reinforced Self-Attention Network: a Hybrid of Hard and Soft Attention for Sequence Modeling arXiv:1801.10296