Self-Distillation Mixup Training for Non-autoregressive Neural Machine Translation.
Jiaxin GuoMinghan WangDaimeng WeiHengchao ShangYuxia WangZongyao LiZhengzhe YuZhanglin WuYimeng ChenChang SuMin ZhangLizhi LeiShimin TaoHao YangPublished in: CoRR (2021)
Keyphrases
- machine translation
- autoregressive
- moving average
- non stationary
- cross lingual
- language independent
- information extraction
- gaussian markov random field
- cross language information retrieval
- natural language
- natural language processing
- statistical machine translation
- chinese english
- target language
- brazilian portuguese
- random fields
- multilingual documents
- sar images
- machine translation system
- language resources
- text classification
- co occurrence
- query translation
- word alignment
- supervised learning