BERT-MRC+DSC

Reported on 4 benchmarks across 1 task · 1 paper · 3 SOTA

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

Natural Language Processing4 results

Named Entity Recognition (NER)onOntonotes v5 (English)
F1· uses extra data· 2019-11-07
92.07
SOTA
Dice Loss for Data-imbalanced NLP Tasks arXiv:1911.02855
Named Entity Recognition (NER)onMSRA
F1· uses extra data· 2019-11-07
96.72
SOTA
Dice Loss for Data-imbalanced NLP Tasks arXiv:1911.02855
Named Entity Recognition (NER)onOntoNotes 4
F1· uses extra data· 2019-11-07
84.47
SOTA
Dice Loss for Data-imbalanced NLP Tasks arXiv:1911.02855
Named Entity Recognition (NER)onCoNLL 2003 (English)
F1· uses extra data· 2019-11-07
93.33
best: 94.6 (ACE + document-context)
Dice Loss for Data-imbalanced NLP Tasks arXiv:1911.02855