BiLSTM-CRF+ELMo

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

Named Entity Recognition (NER)onCoNLL 2003 (English)
F1· uses extra data· 2018-02-15
92.22
best: 94.6 (ACE + document-context)
SOTA
Deep contextualized word representations arXiv:1802.05365
Named Entity Recognition (NER)onCoNLL++
F1· 2018-02-15
93.42
best: 96.12 (LUKE + SubRegWeigh (K-means))
SOTA
Deep contextualized word representations arXiv:1802.05365