Flair embeddings

Reported on 4 benchmarks across 4 tasks

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
97.85
best: 98.15 (SALE-BART encoder)
Named Entity Recognition (NER)onCoNLL 2003 (English)
F1· uses extra data
93.09
best: 94.6 (ACE + document-context)
ChunkingonPenn Treebank
F1 score
96.72
best: 97.3 (ACE)
Shallow SyntaxonPenn Treebank
F1 score
96.72
best: 97.3 (ACE)