Contributions of Transformer Attention Heads in Multi- and Cross-lingual Tasks.
Weicheng MaKai ZhangRenze LouLili WangSoroush VosoughiPublished in: ACL/IJCNLP (1) (2021)
Keyphrases
- cross lingual
- transfer learning
- machine translation
- language modeling
- cross language
- event extraction
- language independent
- cross lingual information retrieval
- parallel corpus
- text classification
- neural network
- translation model
- mono lingual
- news articles
- data mining
- semi supervised
- statistical machine translation
- bayesian networks
- feature selection
- information retrieval