DeBERTa-Ensemble

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· 2020-06-05
98.4
best: 100 (PaLM 540B (finetuned) )
SOTA
DeBERTa: Decoding-enhanced BERT with Disentangled Attention arXiv:2006.03654
Word Sense DisambiguationonWords in Context
Accuracy· 2020-06-05
77.5
best: 85.3 (COSINE + Transductive Learning)
SOTA
DeBERTa: Decoding-enhanced BERT with Disentangled Attention arXiv:2006.03654