The FLORES Evaluation Datasets for Low-Resource Machine Translation: Nepali-English and Sinhala-English.
Francisco GuzmánPeng-Jen ChenMyle OttJuan Miguel PinoGuillaume LamplePhilipp KoehnVishrav ChaudharyMarc'Aurelio RanzatoPublished in: EMNLP/IJCNLP (1) (2019)
Keyphrases
- machine translation
- cross lingual
- target language
- statistical machine translation
- brazilian portuguese
- natural language processing
- cross language information retrieval
- mt evaluation
- language independent
- machine translation system
- language resources
- information extraction
- language processing
- chinese english
- language specific
- query translation
- natural language
- parallel corpus
- word sense disambiguation
- parallel corpora
- word alignment
- word level
- source language
- natural language generation
- machine readable dictionaries
- machine transliteration
- out of vocabulary
- probabilistic model
- machine learning
- data mining