Merge and Label

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 Processing3 results

Named Entity Recognition (NER)onACE 2005
F1· 2019-06-30
82.4
best: 90.9 (Ours: cross-sentence ALB)
SOTA
Merge and Label: A novel neural network architecture for nested NER arXiv:1907.00464
Nested Mention RecognitiononACE 2005
F1· 2019-06-30
82.4
best: 85.46 (BoningKnife)
SOTA
Merge and Label: A novel neural network architecture for nested NER arXiv:1907.00464
Named Entity Recognition (NER)onACE 2005
F1· uses extra data· 2019-06-30
82.4
best: 90.9 (Ours: cross-sentence ALB)
Merge and Label: A novel neural network architecture for nested NER arXiv:1907.00464