DuRecDial
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
DuRecDial 2.0
45.84F1
14
DuRecDial
47.43F1
14
DuRecDial OOD (test)
4.81Coherence
11
DuRecDial OOD 2.0 (test)
1.3Perplexity
8
DuRecDial ID 2.0 (test)
1.28PPL
8
DuRecDial OOD 1.0 (test)
1.45Perplexity (PPL)
8
DuRecDial ID 1.0 (test)
1.46PPL
8
DuRecDial OOD 2.0 (test)
4.07Proactivity
7
DuRecDial ID 2.0 (test)
3.86Proactivity
7
DuRecDial ID (test)
4.21Proactivity
7
DuRecDial
1.121Dist-2 Score
7
DuRecDial
19.52R@1
7
DuRecDial 2.0
97.68Dialog Action Accuracy
6
DuRecDial
97.11Action Accuracy
6
DuRecDial OOD 2.0 (test)
6.46PPL
5
DuRecDial ID 2.0 (test)
3.93PPL
5
DuRecDial OOD (test)
4.17Perplexity
5
DuRecDial ID (test)
3.31Perplexity (PPL)
5
DuRecDial OOD 2.0 (test)
3.03Proactivity
4
DuRecDial ID 2.0 (test)
2.9Proactivity
4
DuRecDial ID (test)
3.17Proficiency
4