An Empirical Study of Leveraging Knowledge Distillation for Compressing Multilingual Neural Machine Translation Models.
Varun GummaRaj DabrePratyush KumarPublished in: CoRR (2023)
Keyphrases
- machine translation
- cross lingual
- language independent
- language resources
- cross language information retrieval
- language processing
- multilingual documents
- statistical translation models
- chinese english
- machine translation system
- information extraction
- knowledge representation
- probabilistic model
- statistical model
- knowledge base
- language specific
- digital libraries
- finite state transducers
- natural language processing
- multilingual information retrieval
- parallel corpora
- information retrieval
- statistical models
- natural language
- natural language generation
- target language
- bilingual lexicon
- word sense disambiguation