Multilingual Denoising Pre-training for Neural Machine Translation.
Yinhan LiuJiatao GuNaman GoyalXian LiSergey EdunovMarjan GhazvininejadMike LewisLuke ZettlemoyerPublished in: CoRR (2020)
Keyphrases
- machine translation
- denoising
- cross lingual
- language independent
- language resources
- cross language information retrieval
- multilingual documents
- chinese english
- language specific
- machine translation system
- cross lingual information retrieval
- parallel corpus
- natural language processing
- language processing
- comparable corpora
- word sense disambiguation
- image processing
- information extraction
- target language
- word alignment
- natural language generation
- statistical machine translation
- cross language
- parallel corpora
- brazilian portuguese
- multilingual information retrieval
- linguistic resources
- query translation
- machine learning
- broadcast news
- sentiment classification
- wordnet
- text classification
- digital libraries
- bilingual lexicon
- machine transliteration
- data mining