NCRF++

Reported on 4 benchmarks across 4 tasks · 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

Part-Of-Speech TaggingonPenn Treebank
Accuracy· 2018-06-14
97.49
best: 98.15 (SALE-BART encoder)
NCRF++: An Open-source Neural Sequence Labeling Toolkit arXiv:1806.05626
Named Entity Recognition (NER)onCoNLL 2003 (English)
F1· 2018-06-14
91.35
best: 94.6 (ACE + document-context)
NCRF++: An Open-source Neural Sequence Labeling Toolkit arXiv:1806.05626
ChunkingonPenn Treebank
F1 score· 2018-06-14
95.06
best: 97.3 (ACE)
NCRF++: An Open-source Neural Sequence Labeling Toolkit arXiv:1806.05626
Shallow SyntaxonPenn Treebank
F1 score· 2018-06-14
95.06
best: 97.3 (ACE)
NCRF++: An Open-source Neural Sequence Labeling Toolkit arXiv:1806.05626