How Much Does Tokenization Affect Neural Machine Translation?
Miguel DomingoMercedes García-MartínezAlexandre HelleFrancisco CasacubertaManuel HerranzPublished in: CICLing (1) (2019)
Keyphrases
- machine translation
- natural language processing
- named entities
- cross lingual
- target language
- information extraction
- word sense disambiguation
- language processing
- cross language information retrieval
- language independent
- chinese english
- statistical machine translation
- natural language generation
- word alignment
- language resources
- natural language
- brazilian portuguese
- associative memory
- language specific
- multilingual documents
- question answering
- tasks in natural language processing