Unicoder: A Universal Language Encoder by Pre-training with Multiple Cross-lingual Tasks.
Haoyang HuangYaobo LiangNan DuanMing GongLinjun ShouDaxin JiangMing ZhouPublished in: CoRR (2019)
Keyphrases
- cross lingual
- parallel corpus
- european languages
- monolingual and cross lingual
- language specific
- machine translation
- language modeling
- linguistic resources
- event extraction
- source language
- cross language
- machine translation system
- language independent
- cross lingual information retrieval
- target language
- transfer learning
- indian languages
- bilingual dictionaries
- news articles
- supervised learning
- active learning
- word alignment
- language model
- mono lingual