Unicoder: A Universal Language Encoder by Pre-training with Multiple Cross-lingual Tasks.
Haoyang HuangYaobo LiangNan DuanMing GongLinjun ShouDaxin JiangMing ZhouPublished in: EMNLP/IJCNLP (1) (2019)
Keyphrases
- cross lingual
- parallel corpus
- european languages
- machine translation
- language specific
- monolingual and cross lingual
- linguistic resources
- transfer learning
- language modeling
- language independent
- cross lingual information retrieval
- cross language
- indian languages
- source language
- machine translation system
- event extraction
- bilingual dictionaries
- cross language information retrieval
- text classification
- natural language
- parallel corpora
- artificial intelligence
- document clustering