Multimodal Machine Translation through Visuals and Speech.
Umut SulubacakOzan CaglayanStig-Arne GrönroosAku RouheDesmond ElliottLucia SpeciaJörg TiedemannPublished in: CoRR (2019)
Keyphrases
- machine translation
- finite state transducers
- audio visual
- language independent
- natural language processing
- multi modal
- information extraction
- cross lingual
- statistical machine translation
- speech recognition
- language processing
- target language
- cross language information retrieval
- chinese english
- speech signal
- natural language generation
- word alignment
- word sense disambiguation
- natural language
- machine translation system
- automatic speech recognition
- source language
- parallel corpora
- multilingual documents
- word level
- parallel corpus
- language resources
- brazilian portuguese