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 1120 of 108 papers

TitleStatusHype
Neural Machine Translation with Phrase-Level Universal Visual RepresentationsCode1
BigVideo: A Large-scale Video Subtitle Translation Dataset for Multimodal Machine TranslationCode1
Self-Knowledge Distillation with Progressive Refinement of TargetsCode1
Tackling Ambiguity with Images: Improved Multimodal Machine Translation and Contrastive EvaluationCode1
Scene Graph as Pivoting: Inference-time Image-free Unsupervised Multimodal Machine Translation with Visual Scene HallucinationCode1
Cross-lingual Visual Pre-training for Multimodal Machine TranslationCode1
3AM: An Ambiguity-Aware Multi-Modal Machine Translation DatasetCode1
MSCTD: A Multimodal Sentiment Chat Translation DatasetCode1
Distill the Image to Nowhere: Inversion Knowledge Distillation for Multimodal Machine TranslationCode1
Incorporating Probing Signals into Multimodal Machine Translation via Visual Question-Answering PairsCode0
Show:102550
← PrevPage 2 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