BERT-SocialIQA 340M

Reported on 2 benchmarks across 2 tasks · 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 Processing2 results

Question AnsweringonCOPA
Accuracy· 2019-04-22
83.4
best: 100 (PaLM 540B (finetuned) )
SOTA
SocialIQA: Commonsense Reasoning about Social Interactions arXiv:1904.09728
Coreference ResolutiononWinograd Schema Challenge
Accuracy· 2019-04-22
72.5
best: 100 (PaLM 540B (fine-tuned))
SOTA
SocialIQA: Commonsense Reasoning about Social Interactions arXiv:1904.09728