Language Tokens: A Frustratingly Simple Approach Improves Zero-Shot Performance of Multilingual Translation.
Muhammad N. ElNokrashyAmr HendyMohamed MaherMohamed AfifyHany Hassan AwadallaPublished in: CoRR (2022)
Keyphrases
- language resources
- cross language information retrieval
- comparable corpora
- parallel corpus
- programming language
- machine translation system
- target language
- natural language
- bilingual dictionaries
- machine translation
- query translation
- language independent
- language specific
- cross language
- cross lingual
- line segments
- database
- language processing
- statistical machine translation
- query expansion
- information extraction
- knowledge representation
- digital libraries
- cross lingual information retrieval