SOTAVerified

Multimodal Machine Translation

Multimodal machine translation is the task of doing machine translation with multiple data sources - for example, translating "a bird is flying over water" + an image of a bird over water to German text.

( Image credit: Findings of the Third Shared Task on Multimodal Machine Translation )

Papers

Showing 7180 of 108 papers

TitleStatusHype
Probing the Need for Visual Context in Multimodal Machine Translation0
Rakuten’s Participation in WAT 2021: Examining the Effectiveness of Pre-trained Models for Multilingual and Multimodal Machine Translation0
Sheffield MultiMT: Using Object Posterior Predictions for Multimodal Machine Translation0
Sheffield Submissions for WMT18 Multimodal Translation Shared Task0
SHEF-Multimodal: Grounding Machine Translation on Images0
Supervised Visual Attention for Simultaneous Multimodal Machine Translation0
The AFRL-Ohio State WMT18 Multimodal System: Combining Visual with Traditional0
The AFRL-OSU WMT17 Multimodal Translation System: An Image Processing Approach0
The Case for Evaluating Multimodal Translation Models on Text Datasets0
The MeMAD Submission to the WMT18 Multimodal Translation Task0
Show:102550
← PrevPage 8 of 11Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1delMeteor (EN-FR)74.6Unverified
2ERNIE-UniX2BLEU (EN-DE)49.3Unverified
3IKD-MMTBLEU (EN-DE)41.28Unverified
4DCCNBLEU (EN-DE)39.7Unverified
5CaglayanBLEU (EN-DE)39.4Unverified
6Gumbel-Attention MMTBLEU (EN-DE)39.2Unverified
7Multimodal TransformerBLEU (EN-DE)38.7Unverified
8ImagiTBLEU (EN-DE)38.4Unverified
9del+objBLEU (EN-DE)38Unverified
10VMMTFBLEU (EN-DE)37.6Unverified
#ModelMetricClaimedVerifiedStatus
1ViTABLEU (EN-HI)51.6Unverified
#ModelMetricClaimedVerifiedStatus
1ViTABLEU (EN-HI)44.6Unverified