Good for Misconceived Reasons: An Empirical Revisiting on the Need for Visual Context in Multimodal Machine Translation.
Zhiyong WuLingpeng KongWei BiXiang LiBen KaoPublished in: CoRR (2021)
Keyphrases
- machine translation
- visual context
- temporal context
- audio visual
- scene interpretation
- natural language processing
- semantic context
- object detection
- visual scene
- information extraction
- target language
- cross language information retrieval
- multi modal
- statistical machine translation
- visual words
- machine translation system
- machine learning
- visual information
- object recognition
- computer vision
- multimedia
- knowledge base