Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Personalized Dialogue Generation on ConvAI2 (Human Evaluation)
Loading...
80
Readability
Ground-Truth
56.08
62.29
68.5
74.71
May 19, 2023
Readability
Diversity
Consistency
Coherence
Updated 4d ago
Evaluation Results
Method
Method
Links
Readability
Diversity
Consistency
Coherence
Ground-Truth
2023.05
80
91
86
97
CLV
N=4
2023.05
79
85
61
81
DHAP
2023.05
77
85
49
69
MSP
2023.05
75
83
51
72
GPT-2
2023.05
73
72
43
69
BoB
2023.05
72
80
57
73
PerCVAE
2023.05
71
82
41
65
Seq2Seq
2023.05
57
69
11
34
Feedback
Search any
task
Search any
task