Conll
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
CoNLL English Brown 2009 (test)
86.05F1 Score
28
CoNLL M2 14
72.6Precision (P)
27
CoNLL English 2003 (dev)
96.9F1 Score
26
CoNLL-2012 (OntoNotes) v5.0 (test)
88.3F1 Score
25
CoNLL German 2009 (test)
94.77UAS
25
CoNLL 2005 (WSJ (in-domain))
88.93F1 Score
24
CoNLL KB-Matching 2003 (test)
94.6F1 Score
24
CoNLL 2003 (test)
93.79Micro F1
23
CoNLL 2012 (dev)
87.36F1
23
CoNLL Brown 2009 (test)
88.27Precision
22
CoNLL 2005 (dev)
87.63F1 Score
22
CoNLL04 (test)
93.8F1 Score
21
CoNLL 2012
97.2F1 Score
21
CoNLL04
72.86F1 Score (NER)
20
CoNLL English 2003 (val)
97.3Micro-F1
19
CoNLL English 2003
94.3F1 Score
19
CoNLL WSJ 2005 (dev)
89.25F1 Score
19
CoNLL16 (blind)
66.35Accuracy
17
CoNLL16 (test)
69.71Accuracy
17
CoNLL 2012
83.1Average F1
17
CoNLL 2009 (Out-of-domain (Brown))
87.2F1 Score
17
CoNLL Brown 2005 (test)
80.5F1 Score
16
CoNLL-10
76.88F0.5 Score
16
CoNLL
0.768MPPC
14
CoNLL16 (blind)
72.33F1 Score
14