BERT-base 110M + MAS

Reported on 2 benchmarks across 2 tasks · 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

Coreference ResolutiononWinograd Schema Challenge
Accuracy· 2019-05-31
60.3
best: 100 (PaLM 540B (fine-tuned))
Attention Is (not) All You Need for Commonsense Reasoning arXiv:1905.13497
Natural Language UnderstandingonPDP60
Accuracy· 2019-05-31
68.3
best: 90 (HNN)
Attention Is (not) All You Need for Commonsense Reasoning arXiv:1905.13497