Flair

Reported on 7 benchmarks across 5 tasks

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing5 results

Named Entity Recognition (NER)onCoNLL 2003 (German) Revised
F1
88.3
best: 92.23 (FLERT XLM-R)
ChunkingonCoNLL 2000
Exact Span F1· uses extra data
96.72
best: 97.3 (ACE)
Text ClassificationonFMC-MWO2KG
Macro F1
0.459
Text ClassificationonFMC-MWO2KG
Micro F1
0.597
Shallow SyntaxonCoNLL 2000
Exact Span F1· uses extra data
96.72
best: 97.3 (ACE)

Methodology2 results

ClassificationonFMC-MWO2KG
Macro F1
0.459
ClassificationonFMC-MWO2KG
Micro F1
0.597