Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Machine Translation Hallucination Mitigation on German-English MT Hallucination Subsets
Loading...
2
F. Score
No reranking
-0.92
18.79
38.5
58.21
Dec 16, 2022
F. Score
S. Score
O. Score
Correct Count
Average Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
F. Score
S. Score
O. Score
Correct Count
Average Score
No reranking
reranking=none
2022.12
2
30
80
93
0.51
COMET-QE
reranking=MC dropout h...
2022.12
59
69
85
93
0.77
ALTI
reranking=MC dropout h...
2022.12
64
73
92
91
0.8
LASER
reranking=MC dropout h...
2022.12
72
73
92
92
0.82
LaBSE
reranking=MC dropout h...
2022.12
74
80
92
94
0.85
XNLI (oracle)
reranking=MC dropout h...
2022.12
75
83
98
97
0.88
Feedback
Search any
task
Search any
task