DICT-MLM: Improved Multilingual Pre-Training using Bilingual Dictionaries.
Aditi ChaudharyKarthik RamanKrishna SrinivasanJiecao ChenPublished in: CoRR (2020)
Keyphrases
- bilingual dictionaries
- cross language information retrieval
- comparable corpora
- cross lingual information retrieval
- linguistic resources
- cross lingual
- parallel corpora
- chinese english
- multiword
- language independent
- query translation
- cross language
- training set
- digital libraries
- clustering algorithm
- machine translation
- semi automatic
- information extraction