Multimodal Transformer
Reported on 4 benchmarks across 2 tasks
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Natural Language Processing4 results
- BLEU (EN-DE)38.7best: 49.3 (ERNIE-UniX2)
- Meteor (EN-DE)55.7best: 58.93 (IKD-MMT)
- BLEU (EN-DE)38.7best: 49.3 (ERNIE-UniX2)
- Meteor (EN-DE)55.7best: 58.93 (IKD-MMT)