VAG-NMT

Reported on 6 benchmarks across 2 tasks · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing6 results

Machine TranslationonMulti30K
Meteor (EN-FR)· 2018-08-24
70.3
best: 77.2 (IKD-MMT)
SOTA
A Visual Attention Grounding Neural Model for Multimodal Machine Translation arXiv:1808.08266
Multimodal Machine TranslationonMulti30K
Meteor (EN-FR)· 2018-08-24
70.3
best: 77.2 (IKD-MMT)
SOTA
A Visual Attention Grounding Neural Model for Multimodal Machine Translation arXiv:1808.08266
Machine TranslationonMulti30K
BLEU (EN-DE)· 2018-08-24
31.6
best: 49.3 (ERNIE-UniX2)
A Visual Attention Grounding Neural Model for Multimodal Machine Translation arXiv:1808.08266
Machine TranslationonMulti30K
Meteor (EN-DE)· 2018-08-24
52.2
best: 58.93 (IKD-MMT)
A Visual Attention Grounding Neural Model for Multimodal Machine Translation arXiv:1808.08266
Multimodal Machine TranslationonMulti30K
BLEU (EN-DE)· 2018-08-24
31.6
best: 49.3 (ERNIE-UniX2)
A Visual Attention Grounding Neural Model for Multimodal Machine Translation arXiv:1808.08266
Multimodal Machine TranslationonMulti30K
Meteor (EN-DE)· 2018-08-24
52.2
best: 58.93 (IKD-MMT)
A Visual Attention Grounding Neural Model for Multimodal Machine Translation arXiv:1808.08266