Li and Choi - RoBERTa

Reported on 2 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 Processing2 results

Question AnsweringonFriendsQA
EM· 2020-04-07
53.5
best: 58.7 (Ma et al. - ELECTRA)
SOTA
Transformers to Learn Hierarchical Contexts in Multiparty Dialogue for Span-based Question Answering arXiv:2004.03561
Question AnsweringonFriendsQA
F1· 2020-04-07
69.6
best: 75.4 (Ma et al. - ELECTRA)
SOTA
Transformers to Learn Hierarchical Contexts in Multiparty Dialogue for Span-based Question Answering arXiv:2004.03561