HSCRF + softdict

Reported on 2 benchmarks across 1 task

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

Natural Language Processing2 results

Named Entity Recognition (NER)onOntonotes v5 (English)
F1· uses extra data
89.94
best: 92.07 (BERT-MRC+DSC)
Named Entity Recognition (NER)onCoNLL 2003 (English)
F1· uses extra data
92.75
best: 94.6 (ACE + document-context)