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