- 专利标题: Semi-supervised translation of source code programs using neural transformers
-
申请号: US17213174申请日: 2021-03-25
-
公开(公告)号: US12045592B2公开(公告)日: 2024-07-23
- 发明人: Colin Bruce Clement , Dawn Drain , Neelakantan Sundaresan , Alexey Svyatkovskiy , Chen Wu
- 申请人: MICROSOFT TECHNOLOGY LICENSING, LLC.
- 申请人地址: US WA Redmond
- 专利权人: Microsoft Technology Licensing, LLC.
- 当前专利权人: Microsoft Technology Licensing, LLC.
- 当前专利权人地址: US WA Redmond
- 主分类号: G06F9/44
- IPC分类号: G06F9/44 ; G06F8/51 ; G06N3/063 ; G06N3/088
摘要:
An automated system for translating source code written in one programming language into a different programming language utilizes a neural transformer with attention trained on semi-supervised data. The model is jointly pre-trained with a masked language model objective and an autoregressive objective on a large unsupervised source code corpus to learn to comprehend the syntactic structure and semantics of source code. The pre-trained model is then fine-tuned with a token-type prediction objective and an autoregressive objective on supervised translation tasks and data augmented tasks to learn to translate source code from one programming language into a different programming language.
公开/授权文献
信息查询