ERNIE-Code: Beyond English-Centric Cross-lingual Pretraining for Programming Languages.
Yekun ChaiShuohuan WangChao PangYu SunHao TianHua WuPublished in: CoRR (2022)
Keyphrases
- cross lingual
- programming language
- program code
- machine translation
- cross language
- language modeling
- language independent
- general purpose
- cross lingual information retrieval
- domain specific languages
- object oriented
- mono lingual
- parallel corpus
- high level
- software engineering
- text classification
- source code
- parallel corpora
- strongly typed
- statistical machine translation
- denotational semantics
- event extraction
- query translation
- indian languages
- language model
- lambda calculus
- translation model
- information retrieval
- document clustering
- monolingual retrieval
- cross language retrieval
- word alignment
- machine translation system
- word sense
- transfer learning