M2BART: Multilingual and Multimodal Encoder-Decoder Pre-Training for Any-to-Any Machine Translation.
Peng-Jen ChenBowen ShiKelvin NiuAnn LeeWei-Ning HsuPublished in: ICASSP (2024)
Keyphrases
- machine translation
- cross lingual
- language independent
- language resources
- cross language information retrieval
- chinese english
- multilingual documents
- language specific
- machine translation system
- finite state transducers
- distributed video coding
- natural language processing
- video codec
- error control
- decoding process
- language processing
- cross lingual information retrieval
- parallel corpus
- word sense disambiguation
- target language
- information extraction
- natural language generation
- rate distortion
- statistical machine translation
- comparable corpora
- query translation
- word alignment
- bilingual dictionaries
- bit rate
- natural language
- bilingual lexicon
- multilingual information retrieval
- video coding
- source language
- motion estimation
- linguistic resources
- wyner ziv
- word level
- translation model
- cross language
- text classification
- digital libraries
- knowledge base