Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
End-to-End Dialog Generation on DuClarifyDial (test)
Loading...
0.45
BLEU-1
PLATO-MT
0.2732
0.3191
0.365
0.4109
Apr 15, 2022
BLEU-1
BLEU-2
METEOR
CIDEr
Diversity (Dist-1)
Diversity (Dist-2)
Appropriateness
Informativeness
Hallucination Rate
Success Rate
Updated 4d ago
Evaluation Results
Method
Method
Links
BLEU-1
BLEU-2
METEOR
CIDEr
Diversity (Dist-1)
Diversity (Dist-2)
Appropriateness
Informativeness
Hallucination Rate
Success Rate
PLATO-MT
Prompt-based continual...
2022.04
0.45
0.37
0.23
2.17
0.007
0.072
96
90
67
69
PLATO-MT
Prompt-based continual...
2022.04
0.41
0.33
0.21
1.89
0.007
0.062
87
89
55
52
MinTL
2022.04
0.32
0.25
0.17
1.8
0.006
0.046
86
88
35
34
PLATO
2022.04
0.32
0.25
0.16
1.28
0.005
0.034
78
88
36
36
UBAR
2022.04
0.28
0.22
0.16
1.7
0.005
0.031
74
87
32
34
Feedback
Search any
task
Search any
task