Integrating Unsupervised Data Generation into Self-Supervised Neural Machine Translation for Low-Resource Languages.
Dana RuiterDietrich KlakowJosef van GenabithCristina España-BonetPublished in: MTSummit (1) (2021)
Keyphrases
- machine translation
- data generation
- target language
- language independent
- cross lingual
- statistical machine translation
- grammar induction
- multilingual documents
- language resources
- machine translation system
- source language
- language processing
- pos tagging
- natural language processing
- query translation
- parallel corpora
- cross language information retrieval
- information extraction
- comparable corpora
- active learning
- word alignment
- data streams
- bilingual dictionaries
- multilingual information retrieval
- chinese english
- streaming data
- natural language
- supervised learning
- word segmentation
- word level
- unsupervised learning
- artificial intelligence
- word order
- parallel corpus
- data sets
- cross language
- pairwise
- text mining
- change detection
- n gram