Tokenization effect on neural machine translation: an experimental investigation for English-Assamese.
Mazida A. AhmedKishore KashyapShikhar Kumar SarmaPublished in: ICCCNT (2023)
Keyphrases
- machine translation
- target language
- cross lingual
- statistical machine translation
- language independent
- natural language processing
- information extraction
- language processing
- cross language information retrieval
- natural language generation
- named entities
- language resources
- machine translation system
- brazilian portuguese
- word sense disambiguation
- natural language
- parallel corpora
- source language
- chinese english
- language specific
- query translation
- english chinese
- statistical translation models
- mt evaluation
- parallel corpus
- word alignment
- word level
- knowledge representation
- artificial intelligence
- data mining