Memory-efficient NLLB-200: Language-specific Expert Pruning of a Massively Multilingual Machine Translation Model.
Yeskendir KoishekenovVassilina NikoulinaAlexandre BerardPublished in: CoRR (2022)
Keyphrases
- language specific
- memory efficient
- cross lingual
- translation model
- machine translation
- language independent
- cross language information retrieval
- language modeling
- cross language
- statistical machine translation
- text classification
- parallel corpus
- machine translation system
- transfer learning
- language model
- parallel corpora
- natural language
- statistical models
- artificial intelligence
- co occurrence
- natural language processing
- word segmentation
- knowledge representation
- out of vocabulary