Supervised Visual Attention for Multimodal Neural Machine Translation.
Tetsuro NishiharaAkihiro TamuraTakashi NinomiyaYutaro OmoteHideki NakayamaPublished in: COLING (2020)
Keyphrases
- machine translation
- visual attention
- biological vision systems
- saliency map
- eye tracking
- eye movements
- visual perception
- vision system
- cross lingual
- target language
- language independent
- information extraction
- visual attention model
- higher level
- word sense disambiguation
- natural language processing
- multi modal
- semi supervised
- cross language information retrieval
- language resources
- salient regions
- statistical machine translation
- natural language
- word alignment
- feature selection
- chinese english
- active learning
- computer vision
- word level
- real time
- object based visual attention
- unsupervised methods
- query translation
- audio visual
- low level
- machine learning