300D CAFE (no cross-sentence attention)

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· 2017-12-30
85.9
best: 94.7 (UnitedSynT5 (3B))
Compare, Compress and Propagate: Enhancing Neural Architectures with Alignment Factorization for Natural Language Inference arXiv:1801.00102
Natural Language InferenceonSNLI
% Train Accuracy· 2017-12-30
87.3
best: 99.7 (+ Unigram and bigram features)
Compare, Compress and Propagate: Enhancing Neural Architectures with Alignment Factorization for Natural Language Inference arXiv:1801.00102