Exploiting Out-of-Domain Parallel Data through Multilingual Transfer Learning for Low-Resource Neural Machine Translation.
Aizhan ImankulovaRaj DabreAtsushi FujitaKenji ImamuraPublished in: MTSummit (1) (2019)
Keyphrases
- transfer learning
- machine translation
- cross lingual
- cross language information retrieval
- data analysis
- data sets
- training data
- data sources
- labeled data
- language resources
- cross language
- knowledge discovery
- data points
- domain specific
- test data
- target domain
- language independent
- domain adaptation
- collaborative filtering
- unlabeled data
- natural language processing
- active learning
- decision trees
- natural language generation
- information retrieval