Crowdsourced Phrase-Based Tokenization for Low-Resourced Neural Machine Translation: The Case of Fon Language.
Bonaventure F. P. DossouChris C. EmezuePublished in: CoRR (2021)
Keyphrases
- machine translation
- target language
- language processing
- machine translation system
- language specific
- statistical machine translation
- natural language
- language resources
- source language
- natural language processing
- language independent
- cross lingual
- cross language information retrieval
- parallel corpus
- chinese english
- multilingual documents
- natural language generation
- phrase based smt
- information extraction
- comparable corpora
- word alignment
- multilingual retrieval
- bilingual dictionaries
- word sense disambiguation
- word order
- parallel corpora
- word level
- knowledge representation
- machine transliteration
- artificial intelligence
- machine learning