Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Dialog Response Generation on FEWSHOTWOZ TV 1.0 (test)
Loading...
32.95
BLEU
SC-GPT
21.9676
24.8188
27.67
30.5212
Feb 27, 2020
BLEU
ERR
Updated 4d ago
Evaluation Results
Method
Method
Links
BLEU
ERR
SC-GPT
backbone=GPT2-Medium,...
2020.02
32.95
3.38
GPT-2
backbone=GPT2-Medium,...
2020.02
28.47
9.44
SC-LSTM
model_type=Semanticall...
2020.02
22.39
64.62
Feedback
Search any
task
Search any
task