FLAT+BERT

Reported on 4 benchmarks across 1 task · 1 paper

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)onWeibo NER
F1· 2020-04-24
68.55
best: 72.77 (BERT-CRF (Replicated in AdaSeq))
FLAT: Chinese NER Using Flat-Lattice Transformer arXiv:2004.11795
Named Entity Recognition (NER)onMSRA
F1· 2020-04-24
96.09
best: 96.72 (BERT-MRC+DSC)
FLAT: Chinese NER Using Flat-Lattice Transformer arXiv:2004.11795
Named Entity Recognition (NER)onResume NER
F1· 2020-04-24
95.86
best: 96.87 (BERT-CRF (Replicated in AdaSeq))
FLAT: Chinese NER Using Flat-Lattice Transformer arXiv:2004.11795
Named Entity Recognition (NER)onOntoNotes 4
F1· 2020-04-24
81.82
best: 84.47 (BERT-MRC+DSC)
FLAT: Chinese NER Using Flat-Lattice Transformer arXiv:2004.11795