Visual Prediction Improves Zero-Shot Cross-Modal Machine Translation.
Tosho HirasawaEmanuele BugliarelloDesmond ElliottMamoru KomachiPublished in: WMT (2023)
Keyphrases
- cross modal
- machine translation
- multi modal
- multimedia retrieval
- information extraction
- natural language processing
- image retrieval
- visual data
- cross language information retrieval
- target language
- multimedia databases
- visual recognition
- visual similarity
- perceptual information
- natural language
- statistical machine translation
- machine translation system
- information retrieval systems
- knowledge representation