Conll
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
CoNLL16 (test)
70.38F1 Score
14
CoNLL 2005 (test)
87.7F1 Score
14
CoNLL Spanish 2009 (test)
94.34UAS
14
CoNLL 2009 (test)
91.86UAS
14
CoNLL English 2009 (test)
95.21UAS
13
CoNLL BN
90.93F1 Score
12
CoNLL EN
93.02F1 Score
12
CoNLL 2014 M2 (test)
69.97Precision
12
CoNLL de 2003 (test)
74.82F1 Score
12
CoNLL Cased (test)
92.8F1 Score
12
CoNLL 2003 Corrected (test)
94.28F1 Score
12
CoNLL 2009 (test)
90.7F1 Score
12
CoNLL04 (test)
71F1 Score
12
CoNLL Czech 2009 (test)
92.83UAS
12
CoNLL Chinese 2009 (test)
94.05UAS
12
CoNLL03 subset2
95Observed F1
11
CoNLL03 subset1
0.922Observed F1
11
CoNLL03 (all)
93.2Observed F1
11
CoNLL 12
97.2Micro F1
11
CoNLL2003 String-Matching (test)
76.62F1 Score
11
CoNLL WSJ 2005 (test)
0.877F1 Score
11
CoNLL (test)
94.7Micro Accuracy
11
CoNLL Chinese 2012 (test)
74.3Average F1 Score
11
CoNLL 2020
95.32F1 Score
10
CoNLL 2014 (test)
72.13Precision (P)
10