Detecting Concrete Visual Tokens for Multimodal Machine Translation.
Braeden BowenVipin VijayanScott GrigsbyTimothy AndersonJeremy GwinnupPublished in: CoRR (2024)
Keyphrases
- machine translation
- information extraction
- natural language processing
- language independent
- language processing
- statistical machine translation
- cross lingual
- cross language information retrieval
- target language
- chinese english
- word sense disambiguation
- natural language generation
- word alignment
- brazilian portuguese
- cross modal
- query translation
- machine translation system
- natural language
- language resources
- parallel corpora
- visual features
- word level
- multilingual documents
- data mining
- image retrieval