ESIM + ELMo

Reported on 4 benchmarks across 2 tasks · 2 papers · 2 SOTA

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

Natural Language Processing4 results

Common Sense ReasoningonSWAG
Dev· 2018-08-16
59.1
best: 86.6 (BERT-LARGE)
SOTA
SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference arXiv:1808.05326
Common Sense ReasoningonSWAG
Test· 2018-08-16
59.2
best: 90.8 (DeBERTalarge)
SOTA
SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference arXiv:1808.05326
Natural Language InferenceonSNLI
% Test Accuracy· 2018-02-15
88.7
best: 94.7 (UnitedSynT5 (3B))
Deep contextualized word representations arXiv:1802.05365
Natural Language InferenceonSNLI
% Train Accuracy· 2018-02-15
91.6
best: 99.7 (+ Unigram and bigram features)
Deep contextualized word representations arXiv:1802.05365