Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Knowledge-based Dialogue Generation on Synthetic dataset Restaurant domain 1.0 (test)
Loading...
26.8
BLEU (1-Hop)
NS-Dial
18.688
20.794
22.9
25.006
Mar 11, 2022
BLEU (1-Hop)
F1 (1-Hop)
BLEU (2-Hop)
F1 (2-Hop)
BLEU (Hop>=3)
F1 (Hop>=3)
BLEU (All)
F1 (All)
Updated 1mo ago
Evaluation Results
Method
Method
Links
BLEU (1-Hop)
F1 (1-Hop)
BLEU (2-Hop)
F1 (2-Hop)
BLEU (Hop>=3)
F1 (Hop>=3)
BLEU (All)
F1 (All)
NS-Dial
Model version=Full model
2022.03
26.8
96.7
24.4
93.1
22.7
92.2
25.1
94.2
DF-Net
2022.03
24.5
91.5
23
84.2
21.1
81
23.3
87.3
GraphDialog
2022.03
23.2
89.9
21.2
82.1
20.6
79.8
21.4
85
GLMP
2022.03
22
90.4
19.1
83.7
18.4
80.4
20.9
86.1
Mem2Seq
2022.03
19
79.8
17.3
69.4
12.4
66.3
17
73.7
Feedback
Search any
task
Search any
task