Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Question Generation on Fairytale QA
Loading...
54.8
ROUGE-L
M
24.744
32.547
40.35
48.153
Sep 22, 2022
ROUGE-L
Updated 3d ago
Evaluation Results
Method
Method
Links
ROUGE-L
M
mode=upperbound
2022.09
54.8
BART
training=fine-tuned, a...
2022.09
52.7
APS + round-trip
type=ensemble
2022.09
43.9
tri-gram + APS + round-trip
type=ensemble
2022.09
43.5
round-trip
selection_criteria=QA...
2022.09
43.4
bi-gram + APS + round-trip
type=ensemble
2022.09
43.1
tri-gram + round-trip
type=ensemble
2022.09
43
bi-gram + round-trip
type=ensemble
2022.09
42.9
Mg
mode=greedy
2022.09
42.4
tri-gram + APS
type=ensemble
2022.09
40.9
averaged prompt score (APS)
selection_criteria=Pro...
2022.09
40.6
bi-gram + APS
type=ensemble
2022.09
40.6
bi-gram
selection_criteria=n-g...
2022.09
40.3
tri-gram
selection_criteria=n-g...
2022.09
40.3
Ms
mode=sample avg
2022.09
39.9
overall prompt score (OPS)
selection_criteria=Pro...
2022.09
39.9
Ms
mode=lowerbound
2022.09
25.9
Feedback
Search any
task
Search any
task