A Visual Attention Grounding Neural Model for Multimodal Machine Translation.
Mingyang ZhouRunxiang ChengYong Jae LeeZhou YuPublished in: EMNLP (2018)
Keyphrases
- machine translation
- visual attention
- neural model
- saliency map
- neural network
- eye tracking
- eye movements
- recurrent neural networks
- vision system
- control scheme
- language independent
- cross lingual
- higher level
- natural language processing
- information extraction
- cross language information retrieval
- multi modal
- visual perception
- target language
- multi layer perceptron
- natural language
- word alignment
- statistical machine translation
- audio visual
- multimedia
- machine translation system
- closed loop
- pso algorithm
- artificial neural networks
- artificial intelligence
- data mining