Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Task-Oriented Dialogue on MultiWOZ Taxi domain 1.0
Loading...
106.3
Combined Score
EWC+RL
46.396
61.948
77.5
93.052
Jul 25, 2021
Combined Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Combined Score
EWC+RL
Belief State=Oracle, A...
2021.07
106.3
Naive+RL
Belief State=Oracle, A...
2021.07
103.4
EWC
Belief State=Oracle, A...
2021.07
97.5
Naive
Belief State=Oracle, A...
2021.07
93.4
EWC+RL
Belief State=Predicted...
2021.07
87.6
EWC
Belief State=Predicted...
2021.07
78.7
Naive+RL
Belief State=Predicted...
2021.07
75.4
Naive
Belief State=Predicted...
2021.07
66.3
Source
Belief State=Oracle, A...
2021.07
55.4
Source
Belief State=Predicted...
2021.07
48.7
Feedback
Search any
task
Search any
task