Supervised Visual Attention for Simultaneous Multimodal Machine Translation.
Veneta HaralampievaOzan CaglayanLucia SpeciaPublished in: J. Artif. Intell. Res. (2022)
Keyphrases
- machine translation
- visual attention
- eye tracking
- saliency map
- vision system
- eye movements
- information extraction
- natural language processing
- cross language information retrieval
- visual perception
- higher level
- multi modal
- cross lingual
- language independent
- target language
- semi supervised
- multimedia
- object based visual attention
- visual attention model
- natural language
- language resources
- machine learning
- word sense disambiguation
- machine translation system
- feature selection
- statistical machine translation
- real time
- salient regions
- word alignment
- chinese english
- human computer interaction
- query translation
- visual saliency
- word level
- unsupervised methods