CA-MTL

Reported on 3 benchmarks across 1 task · 1 paper · 2 SOTA

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

Natural Language Processing3 results

Natural Language InferenceonSciTail
Accuracy· 2020-09-19
96.8
SOTA
Conditionally Adaptive Multi-Task Learning: Improving Transfer Learning in NLP Using Fewer Parameters & Less Data arXiv:2009.09139
Natural Language InferenceonSNLI
% Test Accuracy· 2020-09-19
92.1
best: 94.7 (UnitedSynT5 (3B))
SOTA
Conditionally Adaptive Multi-Task Learning: Improving Transfer Learning in NLP Using Fewer Parameters & Less Data arXiv:2009.09139
Natural Language InferenceonSNLI
% Train Accuracy· 2020-09-19
92.6
best: 99.7 (+ Unigram and bigram features)
Conditionally Adaptive Multi-Task Learning: Improving Transfer Learning in NLP Using Fewer Parameters & Less Data arXiv:2009.09139