Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Conversational Semantic Role Labeling on DuConv
Loading...
89.97
F1 (All)
MLM + SBO + PMO w/ NP Sampling
88.0876
88.5763
89.065
89.5537
May 28, 2021
F1 (All)
F1 (Cross-Dialogue)
F1 (Intra-Dialogue)
Updated 4d ago
Evaluation Results
Method
Method
Links
F1 (All)
F1 (Cross-Dialogue)
F1 (Intra-Dialogue)
MLM + SBO + PMO w/ NP Sampling
alpha=80
2021.05
89.97
86.68
90.31
MLM + SBO + PMO w/ NP Sampling
alpha=50
2021.05
89.34
86.12
89.99
MLM + SBO + PMO
2021.05
89.21
85.98
89.79
MLM + PMO
2021.05
89.1
85.26
89.52
MLM + SBO
2021.05
88.73
84.49
89.23
MLM
2021.05
88.56
84.37
88.97
No Pretraining
2021.05
88.16
83.74
88.71
Feedback
Search any
task
Search any
task