Handling Rare Word Problem using Synthetic Training Data for Sinhala and Tamil Neural Machine Translation.
Pasindu TennagePrabath SandaruwanMalith ThilakarathneAchini HerathSurangika RanathungaPublished in: LREC (2018)
Keyphrases
- machine translation
- word problems
- training data
- natural language processing
- information extraction
- cross language information retrieval
- similar problems
- language independent
- learning algorithm
- cross lingual
- language processing
- machine translation system
- language resources
- statistical machine translation
- word alignment
- brazilian portuguese
- natural language
- parallel corpora
- target language
- indian languages
- multilingual documents
- word sense disambiguation
- chinese english
- finite state transducers
- query translation
- machine transliteration
- information retrieval