Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multimodal Machine Translation on Multi30K 2018 (test)
Loading...
0.395
BLEU
VL-T5
0.27644
0.30722
0.338
0.36878
Feb 4, 2021
BLEU
Updated 1mo ago
Evaluation Results
Method
Method
Links
BLEU
VL-T5
V&L PT=false
2021.02
0.395
T5
Text-only=true
2021.02
0.39
VL-T5
V&L PT=true
2021.02
0.386
VL-T5
Pretraining Images=180K
2021.02
0.386
MeMAD
Data Augmentation=true...
2021.02
0.385
MeMAD
2021.02
0.385
BART
Text-only=true
2021.02
0.333
VL-BART
V&L PT=false
2021.02
0.332
VL-BART
V&L PT=true
2021.02
0.281
VL-BART
Pretraining Images=180K
2021.02
0.281
Feedback
Search any
task
Search any
task
