Good for Misconceived Reasons: An Empirical Revisiting on the Need for Visual Context in Multimodal Machine Translation

8161

Knowledge Triples

Source Entity	Relationship	Target Entity
Neural Multimodal Machine Translation Task	benefitsFrom	Regularization Effect Metric
Neural Multimodal Machine Translation Task	extends	Text Only Translation Models Method
Neural Multimodal Machine Translation Task	requires	Interpretability Metric
Neural Multimodal Machine Translation Task	uses	Multimodal Information OtherEntity