Multimodal machine translation through visuals and speech.
Umut SulubacakOzan CaglayanStig-Arne GrönroosAku RouheDesmond ElliottLucia SpeciaJörg TiedemannPublished in: Mach. Transl. (2020)
Keyphrases
- machine translation
- audio visual
- finite state transducers
- natural language processing
- target language
- language processing
- language independent
- speech recognition
- information extraction
- multi modal
- natural language
- cross lingual
- cross language information retrieval
- language resources
- machine translation system
- natural language generation
- word level
- broadcast news
- statistical machine translation
- word sense disambiguation
- speech signal
- dialogue system
- word alignment
- chinese english
- multilingual documents
- brazilian portuguese
- parallel corpus
- automatic speech recognition
- spontaneous speech
- data mining
- tasks in natural language processing