Pre-Training on Mixed Data for Low-Resource Neural Machine Translation.
Wenbo ZhangXiao LiYating YangRui DongPublished in: Inf. (2021)
Keyphrases
- machine translation
- mixed data
- cross lingual
- target language
- language processing
- information extraction
- language independent
- natural language
- word sense disambiguation
- natural language processing
- natural language generation
- brazilian portuguese
- training set
- cross language information retrieval
- multilingual documents
- word alignment
- similarity function
- data compression
- machine translation system
- language resources
- data sets
- mixture of gaussian distributions
- knn
- parallel corpus
- chinese english
- query translation
- source language
- query processing
- pairwise
- feature extraction
- clustering algorithm
- neural network