Korean-English Machine Translation with Multiple Tokenization Strategy.
Dojun ParkYoungjin JangHarksoo KimPublished in: CoRR (2021)
Keyphrases
- machine translation
- machine translation system
- cross lingual
- target language
- language independent
- information extraction
- brazilian portuguese
- statistical machine translation
- language processing
- natural language processing
- natural language
- cross language information retrieval
- natural language generation
- word alignment
- language resources
- parallel corpus
- chinese english
- word sense disambiguation
- parallel corpora
- target word
- multilingual documents
- language specific
- named entities
- word order
- query translation
- english chinese
- phrase based smt
- mt evaluation